ElevenLabs Voice AI Session & NCRB/NPMFireside Chat

20 Feb 2026 12:00h - 13:00h

ElevenLabs Voice AI Session & NCRB/NPMFireside Chat

Session at a glanceSummary, keypoints, and speakers overview

Summary

The session focused on overcoming India’s language accessibility challenge by creating a unified multilingual layer for the nation’s digital ecosystem [2][5-6][27-28]. Swati illustrated the problem with a farmer who had to travel 40 km to find help filling an English-only form, underscoring that 95 % of digital content is in English while 800 million users lack fluency [21-24][27-28]. Shailendra introduced the Bhashni (also referred to as Pashni) translation plugin, which is already deployed on more than 500 websites and leverages over 350 language models [7-9][19]. The plugin is presented as a lightweight, one-line JavaScript snippet that can be copied and pasted into any site, instantly rendering the entire site in all 22 Indian scheduled languages without backend redesign [37-45][46-49][67-71]. It automatically applies the multilingual feature across all pages, is DBM-compliant and framework-agnostic, and therefore requires no per-page integration [88-89][79-81][90-94].


Key technical capabilities include support for source languages other than English, a “skip-translation” class for elements like calendars or email IDs, and the ability to reorder language lists to prioritize regional languages [104-109][111-117][120-124]. Additional features allow URL redirection to language-specific domains, limiting the language dropdown to a subset, and preventing page reloads in portal forms, while dynamic content is batched to reduce API calls and latency [135-140][141-145][146-151][162-168]. The team emphasized the importance of custom glossaries to preserve domain-specific terminology, handle transliteration, and correct model-generated errors, noting that over 1.5 million glossary entries have been created for clients such as the Ministry of Home Affairs and BSF [190-197][215-226][236-242][246-250][276-283].


To date, more than 400 websites have integrated the plugin, generating over 24 million translation inferences and demonstrating the scalability of the solution [96-98]. The roadmap includes expanding support to 36 Indian languages and 35 international languages, automating glossary uploads, and adding a text-to-speech accessibility bar [190-194][195-197]. In the Q&A, an audience member asked whether the plugin could be used by private or commercial entities, to which Swati replied that separate collaboration agreements exist and private stakeholders can engage via the Bhashni Pavilion [304-306][307-310]. Another question about region-based default languages was met with acknowledgement that the use case is feasible and will be evaluated further [311-317][318-322]. Finally, the presenters affirmed that glossaries are customized per client, ingested into individual solutions, and that model fine-tuning is pursued for domain-specific accuracy, underscoring the ongoing commitment to digital inclusion [330-332][334-336][333-336].


Keypoints


Major discussion points


The pervasive language barrier in India and the need for a multilingual digital infrastructure – Swati opens by highlighting that “everything is available only in one language…Majorly English” despite a nation of “1.4 billion voices” [1-6]. Shailendra reinforces this by describing citizens who “are not being able to understand in English and Hindi” and the difficulty of accessing state-level policies in one’s own language [7-18]. A concrete example is given of a farmer forced to travel 40 km to fill an English form, illustrating the real-world impact of the divide [21-28].


Introduction and demonstration of the Bhashini (Bhajani) Translation Plugin as a lightweight, plug-and-play solution – Swati explains that the plugin “allows any website to be translated into multiple languages…with a one-liner, very lightweight, simple code” that requires only copy-and-paste and no backend overhaul [36-45][67-71]. She shows the integration on a demo site, noting that the same code works across all pages and is “DBM compliant and framework agnostic” [52-58][79-89][92-99].


Key technical features and challenges addressed by the plugin – The team discusses handling source languages other than English, skipping translation for specific elements (e.g., calendars, email IDs) via a “skip translation class” [104-110][111-117]; customizing language order and default language parameters for regional preferences [120-126][128-131]; managing portals without page reloads, dynamic content batching to reduce API calls, and URL redirection for language-specific domains [141-148][152-160][162-168][176-181].


The role of glossaries in improving translation quality and contextual relevance – Swati describes glossaries as essential for “post-translation” adjustments, handling domain-specific terminology, transliteration, and avoiding incorrect literal translations (e.g., “home” → “Ghar” vs. “Mukhya Prash”) [190-214][215-226][241-250][254-262][267-274]. She notes the creation of millions of glossary entries, the need for client-specific customization, and ongoing work to automate glossary ingestion and integrate accessibility features [196-199][330-336].


Audience questions on commercial use, regional default languages, and glossary maintenance – Participants ask whether the solution can be used by private entities, how default languages might be set per region, and how glossaries are maintained or used for model fine-tuning. Swati responds that commercial collaborations are possible via separate agreements, that regional default language changes are technically feasible, and that glossaries are customized per client and can inform fine-tuning pipelines [304-311][312-317][326-333][333-336].


Overall purpose / goal of the discussion


The session aims to present the Bhashini (Bhajani) Translation Plugin as a scalable, low-effort infrastructure for multilingual digital inclusion in India. It demonstrates how the tool can instantly translate existing websites into all 22 scheduled Indian languages, outlines its technical capabilities and real-world deployment experience, and engages stakeholders on practical concerns such as commercial adoption, regional customization, and the management of domain-specific glossaries.


Overall tone and its evolution


– The conversation begins with a problem-oriented, urgent tone, emphasizing the exclusion caused by language barriers.


– It shifts to an enthusiastic, solution-focused tone during the product overview and live demo, highlighting ease of integration and impact.


– The tone becomes technical and explanatory as the speakers delve into specific features, challenges, and implementation details.


– In the Q&A segment, the tone turns collaborative and supportive, addressing audience concerns, clarifying possibilities for private use, and inviting further engagement. Throughout, the tone remains constructive and optimistic about achieving digital inclusivity.


Speakers

Shailendra Pal Singh – Senior General Manager, Bhashani; co-presenter and technical expert on the Bhashini translation plugin and multilingual integration solutions [S2][S1].


Swati Sharma – Presenter and subject-matter expert on language accessibility, multilingual AI solutions and the Bhashini translation ecosystem [S4].


Audience – General audience participants; includes individuals such as Yuv (from Senegal) [S5], Professor Charu (Indian Institute of Public Administration) [S6], and Dr. Nazar (role not specified) [S7].


Additional speakers:


– None.


Full session reportComprehensive analysis and detailed insights

The session opened with Swati Sharma describing India’s stark language divide: a nation of 1.4 billion people and “1.4 billion voices” [1-4] yet the overwhelming majority of online content is offered only in English [5-6]. She quantified the gap, noting that more than 800 million Indians are not fluent in English and that roughly 95 % of digital material is English-only [5-6]. To illustrate the human impact, Swati recounted a farmer who travelled 40 km simply to find someone able to complete an English-language PM Kisan Samman Nidhi form [21-25][S1].


Shailendra Pal Singh then introduced the Bhashni Translation Plugin, the product that underpins the solution. In his remarks the plugin was also called Pashni and, on a few occasions, Bhajani[7-10]. He highlighted that the plugin is already deployed on more than 500 websites and is powered by over 350 language models [11-13], and positioned it within the National Language Translation Mission as a unified multilingual layer for India’s digital ecosystem [30-33].


A live demonstration followed. Swati showed that the plugin can be integrated into any site with a single, lightweight JavaScript one-liner that requires only copy-and-paste and no backend redesign [70-78]. Once the snippet is inserted, the code automatically enables translation of the entire site into all 22 Indian scheduled languages and persists across every page without the need for per-page integration [79-81].


Technical attributes emphasized during the demo included the plugin’s framework-agnostic design, its compliance with the Digital Brand Identity Management (DBM) guidelines for accessibility, and the fact that it operates without any backend overhaul [88-95][92-99].


The presenters then walked through a detailed feature set:


* Direct source-language translation – the plugin can translate from any source language without using English as an intermediary [104-110].


* Skip-translation class – developers can exclude specific elements (e.g., calendars, email addresses) from translation [111-117].


* Custom language ordering – regional languages can be placed first in the selector [120-126].


* Default-language parameter – a preferred default language (e.g., Hindi) can be forced regardless of the site’s original language [128-131].


* Bilingual-site handling – the plugin can detect and skip translation for pages already in a supported language [133-140].


* Limited dropdown – the language selector can be restricted to a subset of languages [141-145].


* Portal no-reload mode – on portal-style sites the plugin works without reloading the page, preserving user-entered data in forms [141-151].


* Mixed-language detection – the system automatically skips segments that are already in the target language [152-160].


* Dynamic-content batching – for high-frequency sites such as the State Bank of India and MyBharat Hotel, content is processed in batches to reduce API calls and stabilise response times [162-168].


* Voice-activated language selection – demonstrated on the Rail Madad site, users can switch languages via voice commands [170-174].


* URL redirection – the plugin can redirect users to language-specific domains [176-181].


A central component of the architecture is the glossary framework, which refines translation quality by incorporating domain-specific terminology, transliterations, and post-translation adjustments. Over 1.5 million glossary entries have been created for clients such as the Ministry of Home Affairs and the Border Security Force [190-226][236-242]. Specific examples included correcting model-generated punctuation errors (“SMT.”) [241-250], resolving hyphenation mismatches [254-262], fixing singular-plural inconsistencies [267-274], and disambiguating abbreviations such as “BN” for “battalion” in BSF documents [276-283]. Glossaries also enable custom translations for proper nouns, ensuring names like “Vakil Saab Bridge” retain their identity across languages [225-226]. The presenters warned that redundant or mismatched entries can degrade output and therefore must be curated carefully [295-299].


Impact metrics were presented: more than 400 websites have integrated the plugin, generating over 24 million translation inferences and creating 1.5 million glossary entries [96-98]. Real-world use cases highlighted include simplifying farmer access to government schemes [21-25], supporting bilingual portals for the Maharashtra Finance Department [133-140], handling high-frequency dynamic content for the State Bank of India and MyBharat Hotel [162-168], and enabling mixed-language detection that automatically skips already-translated segments [152-160].


The roadmap envisions expanding language support to 36 Indian languages and adding 35 international languages [190-194], launching an automated glossary-upload portal to streamline client onboarding, and introducing an accessibility bar with text-to-speech and screen-reader functionality [190-197]. These enhancements are framed as a “technology for dignity” that can reach the last mile of India’s digital population [198-200].


During the Q&A, audience members asked whether the solution could be used by private or commercial entities. Swati confirmed that separate collaboration agreements exist for startups and private organisations, with a dedicated stakeholder team available at the Bhashni Pavilion [??]. A query about region-based default language selection was met with an acknowledgement that there is no technical barrier and the use case will be examined further [??]. Questions on glossary maintenance and model fine-tuning were answered by explaining that glossaries are customised per client, ingested into individual solutions, and can inform fine-tuning pipelines after domain classification [??].


In conclusion, the presenters and audience agreed that India’s digital exclusion is fundamentally a language issue and that the Bhashni Translation Plugin offers a scalable, low-effort infrastructure to overcome it. The discussion progressed from an urgent problem statement to a live plug-and-play demonstration, then to a deep technical exposition, and finally to a collaborative dialogue on broader adoption and future enhancements, signalling strong alignment for continued development and deployment. [5-6][7-10][19][36-45][88-95][96-98][190-197]


Session transcriptComplete transcript of the session
Swati Sharma

accessibility, language accessibility and language inclusivity. We are a country of 1 .4 billion people. More importantly, a country of 1 .4 billion voices. We all think differently, we all speak differently, and we all dream differently. But whenever we go online, everything is available only in one language. Majorly English.

Shailendra Pal Singh

To break the language barrier that exists in our country. And we have different solutions and different integrations that we have. One of them is Pashni translation plugin, which is already sitting on top of more than 500 websites, if I’m not wrong, the exact number. And we are enabling people, we are enabling citizens of India who are essentially not being able to understand in English and Hindi because most of the digital content that you see, primarily the website, maximum you’ll see is a website which is sitting in a state. The default language would be there or English primarily. But then what about rest of the languages? Imagine a scenario that I’m someone from north and I’m living there in Maharashtra.

Mostly you will see the content in Marathi or English. But then what about having the same content? I don’t know English. But I really want to understand what is there. And I want to convert it, the different policies at the state level, different guidelines, different content, maybe creative content, etc. You need to know in my language. So, Bhajani Translation Plugin is one of the engineered solution using all the models that you might already be aware of. 350 plus models from our platform. We have this solution as Peksa Swati.

Swati Sharma

So, as Shailendra Pal mentioned, last year a farmer wanted to apply for the PM Kisan Samman Nidhi. It’s basically a very simple form that the farmer has to fill. But the form was in English. The farmer literally had to travel 40 kilometers only to find somebody who can actually help him out filling the form. This is the language divide. This is the barrier that we are trying to avoid. Eliminate. 800 plus million people. are not fluent in English. And 95 % of the content which is available, it is in English. This is where Bhashni comes into picture. The National Language Translation Mission of India. We are trying to transcend the language barrier. We are creating a unified multilingual layer for India’s digital ecosystem.

We are not just providing language as a feature. We are providing language as an infrastructure. We are encouraging language as the foundation for digital inclusion. Next slide, please. So, like sir introduced, the Bhashni Translation Plugin. It’s a powerful product through which you can have any website being translated into multiple languages, being accessible to all the people in the last mile. And this happens in matter of minutes. Not days. Or months. Or just minutes. This is the power of the product that we are talking about. And you don’t have to rebuild the entire website. You don’t have to redesign it. There is no back -end overhaul. Just one liner, very lightweight, simple code that you can copy and paste onto the website and you will have your website speaking multiple Indian languages.

This is how accessibility is made effortless, inclusion is made scalable, and the last mile reach is made real. So I just want anybody to see. Anybody who can copy and paste. Like we don’t need a developer or a person who knows JavaScript or the entire back -end. just somebody knows copy and paste and we’ll see how with the help of that you can have the entire website multilingual. So anybody who would like to do that? Yes, sir, please.

Shailendra Pal Singh

Maybe, you want to open a website first and show what exactly VashuCast is.

Swati Sharma

So this is the Vashni’s website and here is the plugin that has been integrated on the website. This plugin will help us have the entire website available in all 22 Indian languages. All right, so while we just give a quick glimpse of what Bhajani translation plugin is, it is basically a very lightweight utility, though. you find it very simple but the content that we have on this website primarily is in English and there are other challenges that you that we would like to discuss later on as how this translation plugin brings in though it looks very easy just you clicked on a button and then you do a translation all together but then we’ll discuss more about what are the different challenges we come across not from the fact the engineering side of it but on the language side of it how we cater and have this challenge taken care so this is just a plugin we just wanted to tell you this is how it works but you know if you go back to English then and then you know we will just talk about what you wanted to we’ll continue with that so I just wanted to have a quick demo of how you can integrate this plug -in onto the website so I think some if yes you can come we’ll just see how with the help of just the knowledge of copy and paste we can have the entire code implemented and you’ll have the entire website translated into multiple different languages.

For the purpose of this demo we had created this dummy website and the code for this website is here. So this is the code that none of us would most of us would not understand. And I would like to request sir to just copy and paste the plug -in code that we have. So we want to tell that this website content is only in English and you want to add multi -lingual flavor to it using Bhashini. You can integrate the solution that we have on the top of

Shailendra Pal Singh

That’s what you’ve meant.

Swati Sharma

Yes. So if you can sir just copy and paste this code. The code which is written here. Yes.

Shailendra Pal Singh

Anywhere here.

Swati Sharma

If you can just add a hyphen between translation and plug -in.

Shailendra Pal Singh

Yes.

Swati Sharma

Can you go back to the website? Refresh it. So you can see that the plug -in is added. And we can now have this website available in all 22 Indian Schedule languages. So that’s the power of this code. We’ve taken care of everything that is happening at the back -end. and you just have to copy and paste the code that we’ve created for you. It’s as simple as that.

Shailendra Pal Singh

So Swati, so let’s say I’ve embedded this particular thing on this particular website. Now it is available. There is the icon. What about if I go to next pages, right? Will the system understand that there’s a link in the I chose and I go to any page? It will reflect Hindi or I have to select every time I go to any page as my language, which I chosen as Hindi.

Swati Sharma

So you don’t have to apply this code on every page. The pages of the website will automatically understand that the multilingual feature has to be embedded on all the pages. So if you move on to any other page of the website. So this was just a dummy website that we had created. Let me. Go to Bajni translation plugin. in Bhajani’s website. So if you go to any of the pages, the plugin will remain there. And you will have the multilingual feature added on all the pages of the website, not just the home page. So let’s go back to the slides now. So like we just demonstrated, the code that we have for the plugin that we are talking about is a one -liner, very lightweight, simple integrated, simply integrated code, which you can use to have your website available in all 22 Indian Schedule languages.

It is DBM compliant and framework agnostic. So if you have your website, in different, made in different languages, it’s irrespective of that, the code will be applied to your website and you can use the same code.

Shailendra Pal Singh

So Swati, can you just give some light on what is DBM compliant as how the website is DBM compliant? If I, let’s say I have a government website and I want to include the Bhasini translation plugin onto it, what is this DBM compliant that you talked about?

Swati Sharma

So these are the compliances mentioned in the digital brand identity management compliance book that is available. So for everybody to have an accessible website, the DBM compliance have to be followed. And we have the DBM compliant code with us wherein all the accessibility features like, you know, that happens in the backend, you know, for, any person who is a visually special person who wants to access the website. is able to do that with the help of the technical integrities that we’ve incorporated into the plug -in code that we have. So this is a glimpse of the impact that we’ve already created. We have approximately more than 400 plus websites that are already integrated with Pashni translation plug -in.

From those websites, we get approximately 24 million plus inferences. And we’ve created 1 .5 million plus glossaries. So glossary is something that I will take at a later section during the session only. But just for a short description, glossary enhances the translation in such a manner that the end citizen who is actually consuming the content from the website is able to understand the content. And also, these are the 22 Indian scheduled languages in which the plug -in is available. available. Next slide, please. So while we were creating the plugin, we had to create something that, you know, one size fits all product and which is something very difficult to create because everybody has different requirements and to cater to all those requirements, we had to make one product that can simply be accessed by everybody.

So these are some of the use cases that I will be discussing that our plugin has the capability to resolve to. The first one is that generally what happens in, you know, a product like this, you translate, you know, from English to the target language. But here in our plugin, what we’ve done is that even if your website is, let’s say, created in a language other than English, let’s say Marathi. That can also be translated to the targeted language directly. So you don’t have to first translate the website to English and then move on to the targeted language. You can have the source and target language as per your requirement. So that’s how we’ve not, you know, you don’t have to get into the bridge of creating English as an intermediary to move from one language to another.

Next slide, please. Okay, so when I talk about a website, there are different sections of the website. And not all these sections would you want to translate. For example, the calendar, if there’s a calendar, you would not want it to be translated into, you know, the target language. Including email IDs and, you know, there are certain sections that a lot of people didn’t want to be translated. So there is one class that you can embed that is the skip translation class. Embedding that will help you. Navigate to the, navigate the sections that you don’t want to be translated. So, that’s also one feature that we have with our plugin. Next slide, please. Okay, so, you know, you saw the plugin, right?

There were languages listed in a certain manner in the plugin. So, what happens is at, you know, many regional places, we want the plugin to have the regional languages on top. So, for example, after English, people don’t want to go alphabetically like Assamese, Bengali. They would want their regional language. In this case, they wanted Hindi to come in the, you know, to change the order of the languages that are appearing. And that is also possible. So, if you want your regional language to come on top, you can have that with our plugin. So, you know, majorly what we say is that we would want to… We want to display our website in a certain language.

So for example, if you created the website in let’s say English, but you would want all the users to have the language to be displayed as Hindi first. And probably then they can navigate to their own targeted language. So even if your website, the source language of your website is English, you can, there is a possibility of adding the parameter which can have the source language as Hindi or Marathi or Punjabi as the user requires for all your websites. Next slide please. Okay, so what if your… Your website has the, you know, has been created in two languages. So for example, you’ve created your website in English and Marathi also. So that was the use case that we had with finance department Maharashtra.

So they did not want translation to happen in the Marathi language and the English language, though their source language of, you know, so basically the source language of the website was English and Marathi. So if you want to skip translation for different languages also, you can do that. So in this case, what happens is that the user selects a language. If the language of the source is selected, let’s say, you know, English or Marathi, it will go redirected to the English or the Marathi page of the website. And if the user has selected any other language, it will move on to the normal process of translating it into the target language. Next slide, please. So, you know, sometimes we have portals also.

Yes. So, you know, because we would want to have websites available in all 22 Indian scheduled languages so that we try and reach out to the maximum people. But if that is your use case wherein you would want just three or four languages to be displayed for every user to be seen, you can have that also. So the drop -down will only display four languages in that case? Yes. But it’s always encouraged to have all the languages so that everybody, you know, who’s accessing your website can have the website available. Thank you, then. So, talking about this use case, what happens is that in most of the cases, we also have portals. And in portals, we have forms or, you know, we basically ask input from the user who is using the portal.

So if they apply Bhajani translation plugin and they, you know, move on from one language to another, it will reload the entire page. If it reloads the entire page, whatever the user has filled in, like their details, their name, their email IDs, all that information was lost. So what we did to capture this was that now plugin can also have the portals without the reload picture. So if you don’t want the plugin to reload every time a user selects a language from the drop -down, you can have that. Next slide, please. So this was a very interesting use case. You know, you can see this is how the website was displayed. So the source language of the website is English.

But like we can see, after every English, below every English word. there is a different language. So Haryana written in English, then Haryana written in Hindi. Puducherry written in English and some other language. So here this was use case of handling mixed languages. So what we did here was that whenever the plugin sees that the source language of the plugin is different from what characters it is getting, like here in Haryana, it is getting Hindi characters also, it will skip this translation automatically. So you would not have to skip it at your end. We’ve done it and we’ve created it, we’ve designed the plugin in such a manner that if the source language of the website is, you know, if the contents going for the translation are different from the source language of the website, it will automatically skip the translation.

Next slide, please. So… With certain use cases, what happened was… that there was a lot of dynamic content on the website. So, static content can easily be translated. Like, it is also difficult, but it’s not as difficult as handling the dynamic content. But for certain, like for State Bank of India and for MyBharat Hotel, the dynamic content was changing so rapidly that it was making too many API calls and the response time was getting delayed. So, what we did there was that we intelligently had the code running in such a manner that the dynamic content was, the translation of dynamic content was handled in batches. And that’s how the, you know, API calls, the increased API calls reduced and the response time was stabilized.

Next slide, please. Okay, so now… We all can, you know, navigate to the website. select the target language on the website and have the website available in the target language. But what if somebody cannot navigate, cannot select a language from the drop -down? We also, with Rail Madad, you know, if you go to the Rail Madad’s website, there is a mic button. So you just say out your language. So for example, if you say out Gujarati, the entire website will turn into Gujarati. So that’s the capability of it. Next slide, please. Okay, so this is a very recent use case that we’ve handled. So like you can see here, there is the MSD website. And there is also another domain name, which is Hindi, which is in Hindi.

So what the client wanted was that, you know, once the user selects Hindi as the drop -down, the translation happens, but it also redirects to the… Hindi domain of the website. So that mapping of which language to which domain, that is also something that we have done at our end and you can have URL redirection also. Next slide please. Okay, so what happens, so let me just ask, I hope everybody here understands Hindi, right? What is the translation of home in Hindi? Ghar, Ghray, that’s right, right? But the home tab on the website, if it is getting translated to Ghar, it’s not the correct translation. It should be translated to Mukhya Prash. So these kind of use cases wherein the translation which is being given by the model is correct but you would want a specific different translation for a specific word or phrases that can also be handled through glossary.

So, the way that we have done this is that we have website. So, we have a lot of information in the information in the Just now, after we complete this, next slide please. So, this is the future roadmap for plugin that we have. We have expanded it to 36 languages, 36 more Indian languages. So, you can go to Vashni Pavilion which is right here in this hall only. We have a demo of the plugin which is available in 36 languages. We are also incorporating the 35 international languages. We have done that for certain use cases which are displayed here today at Bhaat Mandapam. Secondly, we will be talking about glossary but the glossary in, you know, traditionally the glossaries were sent to us through emails and there was a process to, you know, process the glossaries and then ingest it.

But now, we are also planning to get it automated wherein, you can just simply upload the glossary from your onboarding portal. and third, we are also adding the accessibility bar to the plugin. So if you want to have text -to -speech also integrated or screen reader also integrated with the plugin that we just showed, that is also something that we are going to do in some time. So technology for dignity, Bajni Translation plugin would help. It is a powerful tool that will empower you to actually disseminate whatever information you want to, to actually reach the last mile. Moving on to the next segment, which is the glossary. So, you know, we all of us here, we would have some application, some website developed for…

the ease of the user. We would want a person, a student who is registering for a form who can actually do we would want the person to do it in their own preferred language. We would want a farmer to listen to the schemes that are available for him in his preferred language. We would want an Angadwari worker to have the schemes that are available for her told to her in her own language. So that is all what we are working for. We are working for inclusivity and we are working for accessibility. Next slide please. So while we do that we also add Bhashni’s layer to all our solutions or websites to have the actual information reach the last mile.

But generally what happens is that you know we get a remark that the translation is not correct. It is wrong. And after doing analysis with most of our customers we realize that the audience, that the users who are trying to actually use our product, they are not looking for accurate translations. They are looking for understanding the content, the intent of the content which is there on the solution on the website that they have created. And this is not the result, you know, for this we don’t have to focus on getting the accuracy of the translation. We actually have to focus on the context of the translation, use case of the translation, domain of the translation.

So when we realize that, we understood the concept of glossary and that’s how glossary was formed. Next slide please. Now you all would be, you know, waiting for, to understand what glossary is all about. So glossary saw… It involves two kinds of use cases. One is the post -translation that I just told you before. That, you know, home being translated to ghar in Hindi is absolutely right. But home being translated to home tab being translated to ghar is probably not correct. So post translation wherein you would want home to appear as Mukhya Prasht on the tab, home tab, that is something that we cater through with glossary. The second use case is like in the example, there is a bridge called Vakil Saab Bridge in Gujarat.

So Vakil Saab Bridge if translated to English would become something like Lawyer Bridge or something. We wouldn’t want that. Vakil Saab Bridge is our coined terminology and we would want it to retain its identity. We would want Vakil Saab Bridge to be written as Vakil Saab Bridge only in English. And this is the use case of transliteration. So these two kind of use cases are solved through glossary. What we do is we create. We create these glossaries with our customers and we ingest it to the customer’s specific API. Next slide, please. So, you know, like I told you the meaning of glossary, all of us here have different glossaries. Like, you know, the science domain glossaries are different.

Gen Z has a different glossary altogether. You know, any region would have a specific kind of a glossary. So all of these glossaries have to be created with us. And, you know, the customers who created those glossaries have got the translation, which are accepted by the end user, which are understood by the end user. Like you can see, Ministry of Panchayati Raj gave us 15 lakh words of the Panchayat. Survey of India has given us 16 lakh words. So if we create glossaries together, we can have the translation barrier completely eliminated. So I will now walk you through certain. Use cases wherein we faced problems with our customers, but they were not. translation issues, they were actually issues that could have been easily resolved through glossary.

So if you can read this sentence here. So this use case, you know, this problem was reported to us by Ministry of Home Affairs where Honourable Home Minister Sir’s profile was not reflecting correctly. So this was the English sentence. Okay. And this was the translation that we were getting. So if anybody can tell me what is the problem here? So because of this full stop, Srimati full stop, SMT full stop, what the model thought was that the sentence has ended here. And that is why the formation of the sentence is entirely incorrect. But the solution was very simple. What we had to do was just add SMT dot to the glossary or just remove the dot from the SMT.

And we could have the correct output. So it’s as simple as that. It’s not the translations problem. It’s the understanding of glossary problem. Next slide, please. So, okay. Can anybody tell me what’s the difference between this and this puzzle? To these two puzzle pieces, what is the difference? Yes. So one of them has a hyphen and the other one does not have a hyphen. So when we received the glossary from MSME, there was a hyphen in between PMS and dashboard. but actually on the website it was displayed without the hyphen. So glossary is that sensitive. If you give me PMS hyphen dashboard, it will only recognize that and translate that. But if there is no hyphen, it will not recognize that and it will not give you the translated output which you have given us in glossary.

So that’s the, and again, here there was a singular and plural problem. So street vendors was mentioned in the glossary sheet that we received. But actually street vendor was mentioned on the website. So if there is a singular and plural difference in the glossary sheet that you are giving to us and what is actually reflected on the website or your solution, it will create a difference. So this is one thing that you can also do through glossary. So, you know, we received. A requirement wherein they wanted, you know, the animal husbandry department wanted that the entire sentence should not be translated. the, you know, abbreviations should be skipped from translation. So if you just give me this sentence and this sentence as glossary pairs in English and Hindi, this can easily be achieved.

Next slide, please. Okay, so in one of the glossaries that we received was authorized officer, so they wanted us to write authorized officer as newt adhikari. But actually, newt adhikari means appointed officer. So this is also something that we have to be careful of. Because, you know, for the end user, so there are two kind of users that we have in this case, the English users and the Hindi users. So the English user would read it as authorized officer, but since we have added glossary and changed it to, newt adhikari in Hindi, the Hindi user would read it, would understand it as appointed officer. So we have to be very careful while drafting the glossaries.

Next slide please. Okay. So if I can just ask what is the full form of BN? Normally what do we consider as the full form of BN? Billion, right? We would not consider BN as battalion. But in BSF’s case, this was a huge problem. So BN for BSF means battalion and not billion. The entire context changes. So for BSF, we have created glossaries for all the abbreviations. So it is always suggested that you know whatever abbreviations that you are displaying on your website or your solution, just give it to us as glossary so that the correct one can be displayed. So okay. So, So can you tell me if PS to Minister being translated as Maanenya Vastra Mantri Ji ki Iji Sacheev, is there a difference or like what would be the problem here?

Fine, let me tell you. So this is also correct, this is also correct. But this is not the actual translation of PS to Minister. If we want to have Maanenya written in the Hindi translation of it, we should always have it in the English version of it also. Glossaries are supposed to be equal. They are supposed to be equally weighted. You cannot expect the model to add or delete words as their own. So basically what we did here was we went back to the customer and said, that if you want to add Maanenya, you can add Maanenya to the text. at the output, please add respected or honourable in the input. Only then it will be balanced out.

Next slide, please. So this is one request from our end only. We receive a lot of glossaries that are redundant in nature for us. By that I mean that, you know, for example, we received employment and skill development as the glossary terminology and the translation that we are getting in Hindi. That was the actual output of the model also. So in this case, if you are giving us the glossary, which is actually the output of the model, you are only creating redundancy. So if you can just avoid that and give us translations, give us the post -translations or transliterations that are not recognized by the model, that would be handy. Next slide please. Next slide.

So in the end I would just like to say that language is not just words, it is identity. Let us prepare India’s languages for the future of AI and let us create glossaries, let us have multilingual AI in, multilingual layer in all your solutions so that actually the end user is benefited, actually there is digital inclusion, accessibility, inclusivity. Thank you. Any question?

Audience

Can you hear me? So I was saying like the translation thing which you were showing, is it, I know like this has been sponsored by the government and stuff, so can it be also used for commercial purpose like for private or private? Public entity? Can they also use that in their websites also?

Swati Sharma

So, you know, we have different kind of collaborations with us. So for that collaboration, there is a different agreement altogether that is being created. If you want to know more about it, just go to the Bhajani Pavilion. We have stakeholders who are handling the startups, the private organizations also, and they can help you there.

Audience

And one more thing which I wanted to know. So like you were showing for the websites, it was by default we can choose the default language, right? So can it be also extended? Like let’s say in some use cases, we could have someone who is logging in from Delhi. They would want to see it in Hindi and someone who is coming from Maharashtra. So can it change the default languages? Can it change from the region perspective?

Swati Sharma

So that’s an interesting use case. From what I’ve understood, you want different regions to have websites opened in different default languages. As per my knowledge, I don’t see a technical challenge to it. But again, we will have to look at the use case at our end and see if this can be deferred. It’s a very use case. This is a very interesting use case. We’ll look at it. Thank you.

Audience

Hi. Hi. So we all are aware that we have multilingual languages. And apparently, they have been trained on a lot of words also according to their domain knowledge. So if we have glossaries, how do we ensure that each and every glossary according to the domain is maintained and then trained or fine -tuned?

Swati Sharma

So glossaries are customized. For example, somebody from Ministry of Home Affairs would not want the glossary of, let’s say, CSI. Right. Right. you know the domains are different the contexts are different so glossaries are ingested only are customized and are ingested to the client itself they are not we have general glossaries also that can be applied to all but since glossary does not have the you know one glossary fits all type of a solution so we customize it for a client and then ingest it on to that client solution itself not to other clients or other environments.

Audience

Thanks So the glossaries you have do you have them do you use them to fine tune your models or is it just available as documents to infer while using?

Swati Sharma

So we do that we try to fine tune the models as well but we there are lot of things that we have to look at it look around while doing that because you know we have to classify them into different domains and then apply fine tuning models for the domain space. So it’s a long process, but we do that. Okay. Thank you. If there are any other questions, I will be available at the Bhashni Pavilion here also. And I would request everybody to please come visit us, explore our solutions, explore our services. And thank you so much for being a lovely audience. Thank you.

Related ResourcesKnowledge base sources related to the discussion topics (25)
Factual NotesClaims verified against the Diplo knowledge base (3)
Confirmedhigh

“India has 1.4 billion people and the overwhelming majority of online content is offered only in English”

The knowledge base explicitly states that India has 1.4 billion people with diverse languages, but most online content is only available in English, confirming the claim [S1].

!
Correctionmedium

“Roughly 95 % of digital material is English‑only”

A source reports that 75 % of Internet content lacks language diversity, which differs from the 95 % figure cited in the report, indicating the claim may overstate the proportion [S27].

Additional Contextlow

“The plugin can translate the entire site into all 22 Indian scheduled languages”

India’s constitution recognises 22 scheduled languages, providing the linguistic scope the plugin aims to cover, but the source does not verify the plugin’s capability; it only confirms the number of languages [S15].

External Sources (61)
S1
ElevenLabs Voice AI Session & NCRB/NPMFireside Chat — -Shailendra Pal Singh: Role/title not explicitly mentioned, but appears to be a co-presenter/expert on Bhashini translat…
S2
Digital Democracy Leveraging the Bhashini Stack in the Parliamen — -Shailendra Pal Singh- Senior General Manager, Bhashani
S3
https://dig.watch/event/india-ai-impact-summit-2026/digital-democracy-leveraging-the-bhashini-stack-in-the-parliamen — mostly from my understanding and experience with the English that has happened, in the past. Yeah. interesting points, P…
S4
ElevenLabs Voice AI Session & NCRB/NPMFireside Chat — -Swati Sharma: Role/title not explicitly mentioned, but appears to be a key presenter/expert on Bhashini translation sol…
S5
WS #280 the DNS Trust Horizon Safeguarding Digital Identity — – **Audience** – Individual from Senegal named Yuv (role/title not specified)
S6
Building the Workforce_ AI for Viksit Bharat 2047 — -Audience- Role/Title: Professor Charu from Indian Institute of Public Administration (one identified audience member), …
S7
Nri Collaborative Session Navigating Global Cyber Threats Via Local Practices — – **Audience** – Dr. Nazar (specific role/title not clearly mentioned)
S8
Criss-cross of digital margins for effective inclusion | IGF 2023 Town Hall #150 — Pavel Farhan:goal. Thank you. All right. Hi again, this is Pavel for The Record. I guess the benefit of going last is At…
S9
WS #144 Bridging the Digital Divide Language Inclusion As a Pillar — An audience member (Gabriel) raised practical implementation barriers, noting that font rendering and screen reader acce…
S10
Digital Inclusion Through a Multilingual Internet | IGF 2023 WS #297 — Additionally, the lack of devices or platforms that support specific languages can further hamper internet usage. Furthe…
S11
Digital inclusivity – Connecting the next billion — With over 90% of online content being exclusively in English, non-English speakers who depend on native language resourc…
S12
Main Session 1: Global Access, Global Progress: Managing the Challenges of Global Digital Adoption — Shivnath Thukra: Thanks to you and thanks for inviting me, Meta from India on this panel. I will, in the spirit of bein…
S13
https://dig.watch/event/india-ai-impact-summit-2026/elevenlabs-voice-ai-session-ncrb-npmfireside-chat — But like we can see, after every English, below every English word. there is a different language. So Haryana written in…
S14
Science AI & Innovation_ India–Japan Collaboration Showcase — Yeah, I think I think sort of agree to what everybody has talked about. I think with AI and the smartphone and we are on…
S15
Open Forum #36 Challenges & Opportunities for a Multilingual Internet — Pradeep Kumar Verma: I think I’m audible. So I will be presenting two case studies from India. So one is on the Bhasa…
S16
WSIS Action Line C2 Information and communication infrastructure — Aleksandra Jastrzebska: Thank you so much, Gonzalo. So good morning, everyone. I’m Aleksandra Jastrzemska, a recent grad…
S17
Bridging the Digital Skills Gap: Strategies for Reskilling and Upskilling in a Changing World — Himanshu Rai: Thank you very much. It’s always useful to be the last speaker because I can claim that I had the last wor…
S18
WS #119 AI for Multilingual Inclusion — Developers face technical challenges when accommodating non-Latin scripts in their systems. This includes issues with em…
S19
Safe and Responsible AI at Scale Practical Pathways — He notes that LLMs stumble on domain‑specific terms and suggests combining a glossary (or knowledge graph) with the mode…
S20
ElevenLabs Voice AI Session & NCRB/NPMFireside Chat — And one more thing which I wanted to know. So like you were showing for the websites, it was by default we can choose th…
S21
WS #179 Navigating Online Safety for Children and Youth — 3. Cultural Differences: The need for region-specific policies due to cultural variations was emphasised, complicating e…
S22
https://dig.watch/event/india-ai-impact-summit-2026/elevenlabs-voice-ai-session-ncrb-npmfireside-chat — From those websites, we get approximately 24 million plus inferences. And we’ve created 1 .5 million plus glossaries. So…
S23
OpenAI enhances model performance and customisation options — OpenAIhas unveilednew features to enhance model performance and customizability, catering to developers seeking to optim…
S24
Digital Inclusion Through a Multilingual Internet | IGF 2023 WS #297 — Additionally, community networks are emerging as a technological solution to provide connectivity even in remote areas. …
S25
Criss-cross of digital margins for effective inclusion | IGF 2023 Town Hall #150 — Pavel Farhan:goal. Thank you. All right. Hi again, this is Pavel for The Record. I guess the benefit of going last is At…
S26
Open Forum #29 Advancing Digital Inclusion Through Segmented Monitoring — Pria Chetty: For us, this work is core to our organization, and so we’ve been running for a number of years our after-ac…
S27
Digital divides & Inclusion — Collaboration could involve sharing best practices, providing technical assistance, and advocating for policies that pro…
S28
Science as a Growth Engine: Navigating the Funding and Translation Challenge — And so we actually see this manifest a lot because, you know, there’s been an explosion of drug discovery, and discovere…
S29
ITU’s Call for Input on WSIS+20 — Economic | Development Resource Mobilization and Funding Challenges The private sector derives significant benefits fr…
S30
Promoting policies that make digital trade work for all (OECD) — Lastly, the analysis highlights the importance of involving the private sector in policy decision making. It advocates f…
S31
Public-Private Partnerships in Online Content Moderation | IGF 2023 Open Forum #95 — Another key argument presented is the significance of having a legal framework in place to enable and support these part…
S32
Keynote-Alexandr Wang — “That’s transformative, perhaps most especially in countries like India, where so many languages are spoken.”[11]. “That…
S33
Leaders TalkX: Local to global: preserving culture and language in a digital era — Government-led national strategies are essential for language preservation Goyal presents India’s Bhasani program as a …
S34
ElevenLabs Voice AI Session & NCRB/NPMFireside Chat — The human impact of this divide was illustrated through a compelling anecdote about a farmer who needed to travel 40 kil…
S35
WSIS Action Line C8: Multilingualism in the Digital Age: Inclusive Strategies for a People-Centered Information Society — Tawfik Jelassi: Thank you, Davide. Ladies and gentlemen, colleagues, good morning to all of you and thank you for joinin…
S36
https://dig.watch/event/india-ai-impact-summit-2026/elevenlabs-voice-ai-session-ncrb-npmfireside-chat — But like we can see, after every English, below every English word. there is a different language. So Haryana written in…
S37
Open Forum #13 Bridging the Digital Divide Focus on the Global South — Tripti Sinha identifies language as a significant barrier to Internet participation, noting that millions of users still…
S38
Digital Inclusion Through a Multilingual Internet | IGF 2023 WS #297 — Audience:Thank you. I want to share a view from a regular user’s perspective. One of the main barriers is actually a lac…
S39
Safe and Responsible AI at Scale Practical Pathways — On contextualisation, Srivastava noted that while large language models are improving at general tasks, they consistentl…
S40
How the Global South Is Accelerating AI Adoption_ Finance Sector Insights — Leverage newly announced Indian sovereign language models as interim solutions while waiting for global companies to est…
S41
Lightning Talk #90 Tower of Babel Chaos — This brutally honest reaction captures the real human cost of language barriers – the physical and emotional stress of b…
S42
WS #225 Bridging the Connectivity Gap for Excluded Communities — The discussion maintained a professional but increasingly urgent tone throughout. It began optimistically with solution-…
S43
WS #144 Bridging the Digital Divide Language Inclusion As a Pillar — Christian Daswon: Thanks Ram. I’m really glad that Jen brought up cyber security. I think that’s a very important topic….
S44
Comprehensive Report: Cyber Fraud and Human Trafficking – A Global Crisis Requiring Multilateral Response — The tone began as deeply concerning and urgent, with speakers emphasizing the gravity and scale of the problem. However,…
S45
WS #53 Promoting Children’s Rights and Inclusion in the Digital Age — This comment sets an urgent and action-oriented tone for the discussion, emphasizing the critical nature of child online…
S46
AI for Safer Workplaces & Smarter Industries Transforming Risk into Real-Time Intelligence — The discussion maintained an optimistic and collaborative tone throughout, with speakers consistently emphasizing human …
S47
Lightning Talk #34 Digital Cooperation for Sustainable Heritage Preservation — The tone is consistently enthusiastic, informative, and solution-oriented throughout the presentation. The speaker maint…
S48
Fireside Conversation: 01 — The conversation maintained an optimistic and collaborative tone throughout, with both speakers expressing enthusiasm ab…
S49
WS #6 Bridging Digital Gaps in Agriculture & trade Transformation — The tone was largely optimistic and solution-oriented. Speakers were enthusiastic about the potential of the Internet Ba…
S50
Transforming Health Systems with AI From Lab to Last Mile — The discussion maintained a cautiously optimistic and collaborative tone throughout. It began with enthusiasm about AI’s…
S51
AI as critical infrastructure for continuity in public services — The discussion maintained a collaborative and constructive tone throughout, with participants building on each other’s p…
S52
WS #198 Advancing IoT Security, Quantum Encryption & RPKI — The tone was primarily informative and forward-looking, with speakers providing technical explanations as well as policy…
S53
Advancing Scientific AI with Safety Ethics and Responsibility — The discussion maintained a collaborative and constructive tone throughout, characterized by technical expertise and pol…
S54
Strengthen Digital Governance and International Cooperation to Build an Inclusive Digital Future — The discussion maintained a consistently collaborative and optimistic tone throughout, with speakers emphasizing partner…
S55
Discussion Report: AI Implementation and Global Accessibility — The tone was consistently optimistic and collaborative throughout the conversation. Both speakers maintained a construct…
S56
Open Forum #60 Cooperating for Digital Resilience and Prosperity — The discussion maintained a consistently collaborative and constructive tone throughout. It was professional yet engagin…
S57
Leaders TalkX: Building inclusive and knowledge-driven digital societies — The discussion maintained a professional and collaborative tone throughout, with speakers sharing both achievements and …
S58
Business Engagement Session: Sustainable Leadership in the Digital Age – Shaping the Future of Business — The discussion maintained a consistently collaborative and optimistic tone throughout. It began with academic framing bu…
S59
Advocacy to Action: Engaging Policymakers on Digital Rights | IGF 2023 — A large portion of population is digitally illiterate
S60
https://dig.watch/event/india-ai-impact-summit-2026/ai-for-social-good-using-technology-to-create-real-world-impact — But I think open networks allows many actors, many innovators to build applications on the edge using AI. And I think we…
S61
How Multilingual AI Bridges the Gap to Inclusive Access — And I think this metric should be driven by what do we want it to be in the cultures and the regions to empower this. An…
Speakers Analysis
Detailed breakdown of each speaker’s arguments and positions
S
Swati Sharma
32 arguments135 words per minute4990 words2203 seconds
Argument 1
Language barrier hampers citizens’ access to digital services
EXPLANATION
Swati points out that most online content in India is only available in English, which creates a barrier for citizens who do not understand that language. This limits their ability to use digital services effectively.
EVIDENCE
She notes that when people go online, everything is available only in one language, primarily English, highlighting the exclusivity of digital content [5-6].
EXTERNAL EVIDENCE (KNOWLEDGE BASE)
The dominance of English online (over 90% of content) creates a disadvantage for non-English speakers, confirming the language barrier issue [S11]; additionally, lack of devices and digital literacy further hampers language-specific internet use [S10].
MAJOR DISCUSSION POINT
Language barrier hampers citizens’ access to digital services
AGREED WITH
Shailendra Pal Singh
Argument 2
Over 800 million Indians are not fluent in English; 95 % of online content is English
EXPLANATION
Swati emphasizes the scale of the problem by stating that more than 800 million Indians lack English proficiency, while the vast majority of digital content is in English. This underscores the need for multilingual solutions.
EVIDENCE
She states that 800 plus million people are not fluent in English and that 95 % of the available content is in English [27-28].
EXTERNAL EVIDENCE (KNOWLEDGE BASE)
Studies show that more than 90% of online content is in English, underscoring the scale of the problem highlighted by the speaker [S11].
MAJOR DISCUSSION POINT
Over 800 million Indians are not fluent in English; 95 % of online content is English
Argument 3
Example of farmer unable to fill PM Kisan Samman Nidhi form due to English‑only interface
EXPLANATION
Swati illustrates the language barrier with a concrete case where a farmer had to travel 40 km to find help filling a government form that was only in English. The example shows real‑world impact on citizens.
EVIDENCE
She recounts that a farmer needed to travel 40 kilometers to find someone who could help him fill the PM Kisan Samman Nidhi form because the form was in English [21-25].
EXTERNAL EVIDENCE (KNOWLEDGE BASE)
A farmer had to travel 40 km to find help because the PM Kisan Samman Nidhi form was only in English, illustrating the real-world impact of the language barrier [S1].
MAJOR DISCUSSION POINT
Example of farmer unable to fill PM Kisan Samman Nidhi form due to English‑only interface
Argument 4
Plugin enables instant multilingual translation of any website via a single lightweight code snippet
EXPLANATION
Swati describes the Bhashini Translation Plugin as a one‑liner that can be copied and pasted into any website, instantly providing multilingual support without extensive development effort. The solution is positioned as fast and effortless.
EVIDENCE
She explains that a single lightweight code snippet can be added to a website, making it multilingual in minutes without rebuilding or redesigning the site [41-45].
EXTERNAL EVIDENCE (KNOWLEDGE BASE)
The Bhashini Translation Plugin is described as a lightweight copy-paste code snippet that can make any website multilingual within minutes [S1].
MAJOR DISCUSSION POINT
Plugin enables instant multilingual translation of any website via a single lightweight code snippet
Argument 5
Works across all pages without needing per‑page integration
EXPLANATION
Swati clarifies that once the plugin code is embedded, every page of the website automatically inherits the multilingual capability, eliminating the need to add code to each individual page.
EVIDENCE
She demonstrates that the plugin persists across navigation and does not require per-page integration, as the pages automatically understand the multilingual feature [79-86].
EXTERNAL EVIDENCE (KNOWLEDGE BASE)
Once embedded, the plugin automatically applies to every page of a site and retains language selection across navigation [S1].
MAJOR DISCUSSION POINT
Works across all pages without needing per‑page integration
Argument 6
Framework‑agnostic, DBM‑compliant, and requires no backend overhaul
EXPLANATION
Swati highlights that the plugin works with any web framework, complies with Digital Brand Management (DBM) standards, and does not require changes to the backend, making it easy to adopt for existing sites.
EVIDENCE
She notes that there is no backend overhaul needed and that the solution is framework-agnostic and DBM-compliant, with accessibility features built into the code [42-44][88-95].
EXTERNAL EVIDENCE (KNOWLEDGE BASE)
The solution works with any web framework, complies with Digital Brand Management (DBM) standards, and does not require backend changes [S1].
MAJOR DISCUSSION POINT
Framework‑agnostic, DBM‑compliant, and requires no backend overhaul
AGREED WITH
Shailendra Pal Singh
Argument 7
Supports 22 Indian scheduled languages; uses 350+ language models
EXPLANATION
Shailendra mentions that the plugin leverages more than 350 language models and can render content in all 22 scheduled Indian languages, providing broad linguistic coverage.
EVIDENCE
He states that the solution uses 350 plus models from their platform [19] and Swati adds that the plugin makes a website available in all 22 Indian scheduled languages [53-54].
EXTERNAL EVIDENCE (KNOWLEDGE BASE)
The platform utilizes over 350 language models to provide translation across all 22 scheduled Indian languages [S13].
MAJOR DISCUSSION POINT
Supports 22 Indian scheduled languages; uses 350+ language models
AGREED WITH
Shailendra Pal Singh
Argument 8
Demonstration of copy‑paste integration on a demo site
EXPLANATION
Swati walks the audience through a live demo where a simple copy‑paste of the plugin code adds multilingual capability to a dummy website, showing the ease of integration.
EVIDENCE
She shows the demo website, requests the copy-paste of the plugin code, and explains that the site’s content is only in English before integration [52-58].
EXTERNAL EVIDENCE (KNOWLEDGE BASE)
A live demonstration showed that copying and pasting the plugin code instantly added multilingual capability to a dummy website [S1].
MAJOR DISCUSSION POINT
Demonstration of copy‑paste integration on a demo site
Argument 9
Clarification that the plugin persists language choice across navigation
EXPLANATION
Swati confirms that after the plugin is added, the selected language remains active when users move to other pages, ensuring a seamless multilingual experience.
EVIDENCE
She asks to refresh the site and shows that the plugin remains, keeping the website available in all 22 languages across pages [67-71].
EXTERNAL EVIDENCE (KNOWLEDGE BASE)
The plugin maintains the selected language when users move to other pages, ensuring a seamless experience [S1].
MAJOR DISCUSSION POINT
Clarification that the plugin persists language choice across navigation
Argument 10
Explanation of DBM compliance and accessibility features embedded in the code
EXPLANATION
Swati explains that DBM compliance ensures accessibility for visually impaired users and that the plugin incorporates technical features to meet these standards.
EVIDENCE
She describes DBM compliance as a set of accessibility features that enable visually impaired users to access the website, with the necessary technical integrity built into the plugin code [92-95].
EXTERNAL EVIDENCE (KNOWLEDGE BASE)
The plugin is DBM-compliant and includes built-in accessibility features for visually impaired users; broader accessibility challenges are discussed in the literature [S1][S9].
MAJOR DISCUSSION POINT
Explanation of DBM compliance and accessibility features embedded in the code
Argument 11
Ability to translate from any source language directly, not only English → target
EXPLANATION
Swati notes that the plugin can translate from any source language (e.g., Marathi) directly to the target language, removing the need for English as an intermediate step.
EVIDENCE
She explains that the plugin can translate directly from a source language other than English, such as Marathi, to the desired target language without using English as a bridge [104-109].
EXTERNAL EVIDENCE (KNOWLEDGE BASE)
The system can translate directly between Indian languages without using English as an intermediate language [S13].
MAJOR DISCUSSION POINT
Ability to translate from any source language directly, not only English → target
Argument 12
“Skip translation” class to exclude calendars, email IDs, etc., from translation
EXPLANATION
Swati introduces a CSS class that can be added to elements that should not be translated, such as calendars or email addresses, giving developers fine‑grained control.
EVIDENCE
She describes the “skip translation” class that can be embedded to prevent translation of specific sections like calendars and email IDs [111-117].
MAJOR DISCUSSION POINT
“Skip translation” class to exclude calendars, email IDs, etc., from translation
Argument 13
Custom language ordering to prioritize regional languages in the UI
EXPLANATION
Swati explains that the plugin allows the ordering of language options so that a regional language (e.g., Hindi) can appear at the top of the list, improving user experience.
EVIDENCE
She shows that the language list can be reordered so that regional languages appear first, such as moving Hindi to the top [119-125].
MAJOR DISCUSSION POINT
Custom language ordering to prioritize regional languages in the UI
Argument 14
Option to limit displayed languages to a subset (e.g., 3‑4)
EXPLANATION
Swati mentions that while the plugin can support all 22 languages, administrators can choose to display only a limited number of languages in the dropdown if desired.
EVIDENCE
She states that the dropdown can be configured to show only three or four languages, though displaying all languages is encouraged [141-145].
MAJOR DISCUSSION POINT
Option to limit displayed languages to a subset (e.g., 3‑4)
Argument 15
Portal handling without page reload to preserve user‑entered data
EXPLANATION
Swati describes an enhancement where language switching on portal forms does not cause a full page reload, thereby retaining any data the user has already entered.
EVIDENCE
She explains that the plugin can be configured to avoid page reloads when a user changes language, preventing loss of entered form data [146-151].
MAJOR DISCUSSION POINT
Portal handling without page reload to preserve user‑entered data
Argument 16
Automatic detection and skipping of mixed‑language content
EXPLANATION
Swati notes that the plugin can automatically detect when content contains characters from a language different from the source and skip translation for those parts, avoiding incorrect translations.
EVIDENCE
She provides a use case where mixed Hindi and English characters are present, and the plugin automatically skips translation of those segments [152-160].
EXTERNAL EVIDENCE (KNOWLEDGE BASE)
The plugin automatically detects mixed-language segments (e.g., Hindi-English code-mix) and skips translation for those parts to avoid errors [S13].
MAJOR DISCUSSION POINT
Automatic detection and skipping of mixed‑language content
Argument 17
Batch processing for dynamic content to reduce API calls and latency
EXPLANATION
Swati explains that for sites with rapidly changing dynamic content, the plugin processes translations in batches, reducing the number of API calls and stabilizing response times.
EVIDENCE
She describes handling dynamic content for State Bank of India and MyBharat Hotel by batching translation requests, which lowered API calls and improved latency [162-168].
MAJOR DISCUSSION POINT
Batch processing for dynamic content to reduce API calls and latency
Argument 18
Voice‑activated language selection via microphone (e.g., Rail Madad)
EXPLANATION
Swati showcases a feature where users can speak the name of a language into a microphone button, and the entire website switches to that language instantly.
EVIDENCE
She demonstrates the mic button on the Rail Madad website that allows users to say a language (e.g., Gujarati) and have the site translate accordingly [169-174].
MAJOR DISCUSSION POINT
Voice‑activated language selection via microphone (e.g., Rail Madad)
Argument 19
URL redirection to language‑specific domains (e.g., MSD Hindi domain)
EXPLANATION
Swati describes a capability where selecting a language not only translates the page but also redirects the user to a domain dedicated to that language, ensuring consistent branding.
EVIDENCE
She explains that when a user selects Hindi on the MSD website, the plugin redirects to the Hindi domain, mapping language to domain [176-181].
MAJOR DISCUSSION POINT
URL redirection to language‑specific domains (e.g., MSD Hindi domain)
Argument 20
Glossaries customize translations, handle post‑translation fixes and transliterations
EXPLANATION
Swati outlines that glossaries are used to fine‑tune translations, correcting specific terms after translation and handling transliteration of proper nouns, ensuring contextual accuracy.
EVIDENCE
She explains that glossaries are used for post-translation adjustments and transliteration, such as keeping coined terms unchanged across languages [215-226].
MAJOR DISCUSSION POINT
Glossaries customize translations, handle post‑translation fixes and transliterations
Argument 21
Creation of over 1.5 million glossaries with clients
EXPLANATION
Swati mentions that more than 1.5 million glossary entries have been created in collaboration with various clients to improve translation quality across domains.
EVIDENCE
She states that they have created 1.5 million plus glossaries with customers [98-100].
MAJOR DISCUSSION POINT
Creation of over 1.5 million glossaries with clients
Argument 22
Examples of glossary impact: correcting punctuation‑induced errors, handling hyphenation, singular/plural mismatches, abbreviation meanings
EXPLANATION
Swati provides several real‑world examples where glossaries corrected translation errors caused by punctuation, hyphen usage, number agreement, and ambiguous abbreviations.
EVIDENCE
She illustrates a punctuation error corrected by adding SMT to the glossary [242-248]; a hyphen mismatch resolved by matching the glossary entry [256-260]; singular/plural differences fixed by aligning glossary terms [262-264]; and abbreviation meanings clarified for ‘BN’ in the BSF context [267-269].
MAJOR DISCUSSION POINT
Examples of glossary impact: correcting punctuation‑induced errors, handling hyphenation, singular/plural mismatches, abbreviation meanings
Argument 23
Emphasis on careful glossary curation to avoid semantic errors
EXPLANATION
Swati warns that incorrect glossary entries can lead to misleading translations, such as misinterpreting ‘authorized officer’ as ‘appointed officer’, and stresses the need for precise terminology.
EVIDENCE
She describes a case where translating ‘authorized officer’ to ‘newt adhikari’ changed the meaning to ‘appointed officer’, highlighting the risk of inaccurate glossaries [270-274].
MAJOR DISCUSSION POINT
Emphasis on careful glossary curation to avoid semantic errors
Argument 24
Glossaries are ingested per client; not shared across unrelated domains
EXPLANATION
Swati clarifies that each client receives a customized set of glossaries tailored to their domain, and these are not reused for other clients to maintain relevance and accuracy.
EVIDENCE
She explains that glossaries are customized per client and ingested only into that client’s solution, not shared across unrelated domains [330-336].
MAJOR DISCUSSION POINT
Glossaries are ingested per client; not shared across unrelated domains
AGREED WITH
Audience
Argument 25
>400 websites integrated, generating >24 million translation inferences
EXPLANATION
Swati shares deployment statistics, indicating that more than 400 websites have adopted the plugin and together have produced over 24 million translation inferences, demonstrating scale.
EVIDENCE
She reports that approximately 400 plus websites are integrated and have generated about 24 million plus inferences [96-98].
EXTERNAL EVIDENCE (KNOWLEDGE BASE)
More than 400 websites have adopted the plugin, collectively producing over 24 million translation inferences [S1].
MAJOR DISCUSSION POINT
>400 websites integrated, generating >24 million translation inferences
Argument 26
Farmer form example illustrating reduction of travel distance for assistance
EXPLANATION
Swati revisits the farmer scenario to show how multilingual translation can eliminate the need for farmers to travel long distances for help with government forms.
EVIDENCE
She recounts the farmer who had to travel 40 km to find assistance because the form was only in English, underscoring the benefit of translation [21-25].
EXTERNAL EVIDENCE (KNOWLEDGE BASE)
The farmer’s 40 km journey to obtain help with an English-only form demonstrates how multilingual translation can eliminate such travel burdens [S1].
MAJOR DISCUSSION POINT
Farmer form example illustrating reduction of travel distance for assistance
Argument 27
Specific client implementations (Maharashtra Finance Dept., State Bank of India, MyBharat Hotel) demonstrating handling of dynamic content and portal forms
EXPLANATION
Swati cites concrete deployments where the plugin addressed challenges such as bilingual source sites, dynamic content, and portal form data retention, showcasing its versatility.
EVIDENCE
She describes the Maharashtra Finance Department use case where both English and Marathi sources are present and need selective translation [133-140]; and the dynamic-content handling for State Bank of India and MyBharat Hotel, where batch processing reduced API calls and latency [165-168].
MAJOR DISCUSSION POINT
Specific client implementations (Maharashtra Finance Dept., State Bank of India, MyBharat Hotel) demonstrating handling of dynamic content and portal forms
Argument 28
Expansion to 36 Indian languages and 35 international languages
EXPLANATION
Swati announces plans to broaden the plugin’s language coverage to include 36 Indian languages and 35 additional international languages, extending its global reach.
EVIDENCE
She states that the roadmap includes expanding to 36 Indian languages and adding 35 international languages [190-194].
MAJOR DISCUSSION POINT
Expansion to 36 Indian languages and 35 international languages
Argument 29
Automated glossary upload via onboarding portal
EXPLANATION
Swati mentions an upcoming feature that will let clients upload glossaries directly through an onboarding portal, streamlining the customization process.
EVIDENCE
She explains that the future roadmap includes automating glossary uploads via the onboarding portal [195-196].
MAJOR DISCUSSION POINT
Automated glossary upload via onboarding portal
Argument 30
Addition of an accessibility bar with text‑to‑speech and screen‑reader support
EXPLANATION
Swati outlines a planned accessibility enhancement that will embed a bar offering text‑to‑speech and screen‑reader capabilities, further improving inclusivity.
EVIDENCE
She notes that an accessibility bar with text-to-speech and screen-reader integration is part of the upcoming features [196-197].
MAJOR DISCUSSION POINT
Addition of an accessibility bar with text‑to‑speech and screen‑reader support
Argument 31
Plugin can be used by private and public entities under separate collaboration agreements
EXPLANATION
Swati clarifies that while the plugin is a government‑backed initiative, private sector entities can also adopt it through distinct collaboration agreements.
EVIDENCE
She states that different collaboration agreements exist for private and public entities and directs interested parties to the Bhashini Pavilion [307-310].
MAJOR DISCUSSION POINT
Plugin can be used by private and public entities under separate collaboration agreements
AGREED WITH
Audience
Argument 32
Availability of stakeholder team at Bhashini Pavilion for private‑sector onboarding
EXPLANATION
Swati points out that a dedicated stakeholder team is present at the Bhashini Pavilion to assist private organisations with onboarding and usage of the plugin.
EVIDENCE
She mentions that stakeholders handling startups and private organisations are available at the Bhashini Pavilion to help with onboarding [307-310].
MAJOR DISCUSSION POINT
Availability of stakeholder team at Bhashini Pavilion for private‑sector onboarding
S
Shailendra Pal Singh
2 arguments127 words per minute360 words169 seconds
Argument 1
Supports 22 Indian scheduled languages; uses 350+ language models
EXPLANATION
Shailendra highlights the technical breadth of the solution, noting that it leverages over 350 language models to provide translation across all 22 scheduled Indian languages.
EVIDENCE
He mentions that the solution uses 350 plus models from their platform [19] and that the plugin supports all 22 Indian scheduled languages [53-54].
EXTERNAL EVIDENCE (KNOWLEDGE BASE)
The platform utilizes over 350 language models to provide translation across all 22 scheduled Indian languages [S13].
MAJOR DISCUSSION POINT
Supports 22 Indian scheduled languages; uses 350+ language models
AGREED WITH
Swati Sharma
Argument 2
Query about DBM compliance for government sites
EXPLANATION
Shailendra asks for clarification on how the plugin meets Digital Brand Management (DBM) compliance requirements, specifically for government websites.
EVIDENCE
He asks, “So Shati, can you just give some light on what is DBM compliant as how the website is DBM compliant?” [90-91].
EXTERNAL EVIDENCE (KNOWLEDGE BASE)
The plugin’s DBM compliance and its relevance for government websites are explained in the product description [S1].
MAJOR DISCUSSION POINT
Query about DBM compliance for government sites
AGREED WITH
Swati Sharma
A
Audience
4 arguments144 words per minute220 words91 seconds
Argument 1
Question on using the plugin for commercial/private websites
EXPLANATION
An audience member inquires whether the government‑sponsored translation plugin can also be deployed on commercial or private sector websites.
EVIDENCE
The participant asks, “Can it be also used for commercial purpose like for private or public entity? Can they also use that in their websites?” [304-306].
EXTERNAL EVIDENCE (KNOWLEDGE BASE)
The solution can be adopted by private sector entities under separate collaboration agreements, as noted in the presentation overview [S1].
MAJOR DISCUSSION POINT
Question on using the plugin for commercial/private websites
AGREED WITH
Swati Sharma
Argument 2
Inquiry about region‑based default language selection
EXPLANATION
Another audience member asks whether the plugin can automatically set default languages based on the visitor’s region, such as showing Hindi for Delhi users and Marathi for Maharashtra users.
EVIDENCE
The question outlines the desire for region-based default language changes: “Can it change the default languages? Can it change from the region perspective?” [311-317].
MAJOR DISCUSSION POINT
Inquiry about region‑based default language selection
Argument 3
Concern about maintaining domain‑specific glossaries and fine‑tuning models
EXPLANATION
An audience participant raises a technical concern about how glossaries for specific domains are maintained and whether they are used to fine‑tune the underlying AI models.
EVIDENCE
The participant asks, “How do we ensure that each glossary according to the domain is maintained and then trained or fine-tuned?” [326-329].
MAJOR DISCUSSION POINT
Concern about maintaining domain‑specific glossaries and fine‑tuning models
AGREED WITH
Swati Sharma
Argument 4
Response that glossaries are customized per client and fine‑tuning is performed but requires domain classification
EXPLANATION
Swati responds that glossaries are indeed customized for each client and that fine‑tuning of models is carried out after classifying content into domains, acknowledging the complexity of the process.
EVIDENCE
She explains that glossaries are customized per client and ingested into the client’s solution, and that they do fine-tune models after classifying domains [330-336].
MAJOR DISCUSSION POINT
Response that glossaries are customized per client and fine‑tuning is performed but requires domain classification
AGREED WITH
Swati Sharma
Agreements
Agreement Points
The language barrier hampers citizens’ access to digital services and must be broken.
Speakers: Swati Sharma, Shailendra Pal Singh
Language barrier hampers citizens’ access to digital services To break the language barrier that exists in our country.
Both speakers stress that most online content is only in English, creating a barrier for the majority of Indians, and that breaking this barrier is essential [5-6][21-25][7-8].
POLICY CONTEXT (KNOWLEDGE BASE)
This concern mirrors the digital inclusion agenda highlighted at IGF 2023, where empowering communities to control their languages was identified as key to overcoming language barriers [S24], and aligns with calls for region-specific policies to address cultural differences [S21].
The Bhashini translation plugin supports all 22 Indian scheduled languages using over 350 language models.
Speakers: Swati Sharma, Shailendra Pal Singh
Supports 22 Indian scheduled languages; uses 350+ language models Supports 22 Indian scheduled languages; uses 350+ language models
Both presenters state that the solution leverages more than 350 models to provide translation into all 22 scheduled Indian languages [19][53-54].
POLICY CONTEXT (KNOWLEDGE BASE)
The claim reflects India’s national Bhashini program, recognized as a large-scale effort supporting 22 regional languages and serving billions of users, underscoring government commitment to multilingual AI [S33]; it also fits within broader AI strategy recommendations for bold, consistent national policies [S32].
The plugin is lightweight, framework‑agnostic, DBM‑compliant and requires no backend overhaul.
Speakers: Swati Sharma, Shailendra Pal Singh
Framework‑agnostic, DBM‑compliant, and requires no backend overhaul Query about DBM compliance for government sites
Swati explains that the code is a one-liner, works with any framework, meets DBM accessibility standards and does not need backend changes, while Shailendra seeks clarification on DBM compliance, confirming its importance [42-44][88-95][90-91].
Both public and private entities can adopt the plugin under separate collaboration agreements.
Speakers: Swati Sharma, Audience
Plugin can be used by private and public entities under separate collaboration agreements Question on using the plugin for commercial/private websites
Swati notes that private and startup stakeholders are available for onboarding, and an audience member asks whether commercial use is allowed, confirming that the plugin can be used beyond government sites [307-310][304-306].
POLICY CONTEXT (KNOWLEDGE BASE)
Public-private collaboration models for digital services are advocated in IGF discussions, emphasizing the need for clear legal frameworks to enable joint adoption of tools [S31], and OECD policy notes stress involving the private sector in decision-making on digital inclusion [S30].
Glossaries are customized per client, ingested into their solutions, and are used for fine‑tuning models.
Speakers: Swati Sharma, Audience
Glossaries are ingested per client; not shared across unrelated domains Concern about maintaining domain‑specific glossaries and fine‑tuning models Response that glossaries are customized per client and fine‑tuning is performed but requires domain classification
Swati clarifies that glossaries are built for each client’s domain and can be used to fine-tune AI models after domain classification, addressing the audience’s technical concerns [330-336][326-329][333-336].
POLICY CONTEXT (KNOWLEDGE BASE)
The use of extensive, client-specific glossaries to enhance translation quality was highlighted in recent sessions reporting over 1.5 million glossaries and their role in fine-tuning AI models [S22]; similar customization capabilities are echoed in OpenAI’s fine-tuning API developments [S23].
Similar Viewpoints
Both presenters emphasize the need to eliminate the English‑only digital divide, highlight the plugin’s extensive multilingual capability (22 languages, 350+ models), and stress its technical openness (framework‑agnostic, DBM‑compliant, no backend changes) [5-6][7-8][19][53-54][42-44][88-95][90-91].
Speakers: Swati Sharma, Shailendra Pal Singh
Language barrier hampers citizens’ access to digital services To break the language barrier that exists in our country. Supports 22 Indian scheduled languages; uses 350+ language models Supports 22 Indian scheduled languages; uses 350+ language models Framework‑agnostic, DBM‑compliant, and requires no backend overhaul Query about DBM compliance for government sites
Unexpected Consensus
Region‑based default language selection can be implemented.
Speakers: Audience, Swati Sharma
Inquiry about region‑based default language selection So that’s an interesting use case. From what I’ve understood, you want different regions to have websites opened in different default languages. As per my knowledge, I don’t see a technical challenge to it.
An audience member asks whether the plugin can automatically set default languages based on the visitor’s region, and Swati confirms that it is technically feasible, showing an unexpected alignment on a nuanced feature request [311-317][318-325].
POLICY CONTEXT (KNOWLEDGE BASE)
Technical feasibility of region-based default language settings was demonstrated in an ElevenLabs session where users from Delhi automatically received Hindi interfaces [S20], reinforcing the policy push for region-specific language defaults [S21].
Private sector entities can adopt a government‑backed translation plugin.
Speakers: Audience, Swati Sharma
Question on using the plugin for commercial/private websites We have different kind of collaborations with us. … stakeholders who are handling the startups, the private organizations also, and they can help you there.
While the plugin originates from a national initiative, both the audience and Swati agree that private companies may use it under separate agreements, which may not have been anticipated given its public-sector framing [304-306][307-310].
POLICY CONTEXT (KNOWLEDGE BASE)
Policy discussions on digital inclusion encourage private sector uptake of government-backed solutions, citing benefits of collaborative frameworks and the need for private participation in multilingual service delivery [S30][S31].
Overall Assessment

The discussion shows strong convergence among speakers on the existence of a language barrier in India, the technical solution offered by the Bhashini translation plugin (multilingual support, lightweight integration, DBM compliance), and the openness of the solution to both public and private sectors. Additional consensus emerged on nuanced features such as region‑based default language settings and the customized use of glossaries for domain‑specific fine‑tuning.

High consensus – the participants largely agree on the problem definition, the adequacy of the proposed technology, and its broad applicability, indicating a solid shared understanding that can drive coordinated implementation across sectors.

Differences
Different Viewpoints
Unexpected Differences
Overall Assessment

The discussion was largely collaborative, with speakers presenting a unified vision of eliminating language barriers through the Bhashini Translation Plugin. Questions from the audience about commercial use, regional default language settings, and glossary maintenance were answered affirmatively, indicating consensus rather than conflict. No substantive disagreements emerged regarding goals, implementation strategies, or policy implications.

Minimal to none. The lack of overt disagreement suggests strong alignment among participants, which bodes well for coordinated rollout and adoption of multilingual digital infrastructure.

Takeaways
Key takeaways
India’s digital ecosystem suffers a massive language barrier, with over 800 million citizens not fluent in English and 95 % of online content in English. The Bhashini Translation Plugin provides instant, site‑wide multilingual translation via a single lightweight code snippet, requiring no backend overhaul. The plugin is framework‑agnostic, DBM‑compliant, and supports all 22 Indian scheduled languages (with plans to add 36 Indian and 35 international languages). Advanced features include direct source‑to‑target translation, skip‑translation classes, custom language ordering, limited language display, portal handling without page reload, automatic mixed‑language detection, batch processing for dynamic content, voice‑activated language selection, and URL redirection to language‑specific domains. A glossary system enables domain‑specific translation accuracy, handling post‑translation fixes, transliterations, and custom terminology; over 1.5 million glossary entries have been created for clients. Real‑world impact: >400 websites integrated, >24 million translation inferences, and concrete use cases such as simplifying farmer form access and handling dynamic content for State Bank of India and MyBharat Hotel. Future roadmap: expand language coverage, automate glossary uploads via an onboarding portal, and add an accessibility bar with text‑to‑speech and screen‑reader support. The plugin can be licensed to private and public entities under separate collaboration agreements, with a stakeholder team available at the Bhashini Pavilion.
Resolutions and action items
Demonstrated copy‑paste integration of the plugin on a demo website; confirmed that the same one‑liner works across all pages. Agreed to investigate and potentially implement region‑based default language selection for websites. Private‑sector organizations can obtain the plugin through a separate collaboration agreement; interested parties directed to the Bhashini Pavilion. Roadmap actions: add 36 Indian and 35 international languages, develop automated glossary upload, and integrate an accessibility bar with TTS/screen‑reader. Swati Sharma offered to be available at the Bhashini Pavilion for further discussions and onboarding.
Unresolved issues
Final decision and implementation timeline for region‑specific default language settings remain pending. Specific licensing terms, pricing, and rollout schedule for commercial/private‑sector use were not detailed. Exact process and timeline for automating glossary ingestion via the onboarding portal were not finalized. Details on the fine‑tuning workflow for domain‑specific models and how clients will manage ongoing glossary updates were not fully addressed.
Suggested compromises
For region‑based default language, Swati acknowledged no technical barrier but proposed a review of the use case before committing to implementation. Private‑sector usage will be accommodated through a separate agreement rather than the standard government framework, balancing open access with governance requirements.
Thought Provoking Comments
Follow-up Questions
Can the Bhashini translation plugin be used for commercial purposes by private or public (non‑government) entities?
Clarification is needed on licensing, agreements, and any restrictions for commercial use of the government‑backed translation solution.
Speaker: Audience (unnamed)
Can the default language of a website be automatically set based on the visitor’s region (e.g., Hindi for Delhi users, Marathi for Maharashtra users)?
Implementing region‑based language defaults would improve user experience, but requires technical feasibility and policy decisions.
Speaker: Audience (unnamed)
How can domain‑specific glossaries be consistently maintained, updated, and incorporated into model training or fine‑tuning?
Ensuring that each sector’s terminology stays current and is reflected in translation quality demands a systematic process for glossary management and model adaptation.
Speaker: Audience (unnamed)
Are glossaries used only at inference time, or are they also employed to fine‑tune the underlying translation models?
Understanding the role of glossaries in model improvement versus runtime substitution informs resource allocation and future development priorities.
Speaker: Audience (unnamed)
What are the technical and resource requirements to expand the plugin’s support from 22 to 36 Indian languages and to add 35 international languages?
Scaling to additional languages involves data collection, model training, evaluation, and possibly new UI/UX considerations.
Speaker: Swati Sharma
How can the glossary ingestion process be automated through an onboarding portal for clients?
Automating glossary upload would streamline deployments and reduce manual effort, but requires design of a secure, user‑friendly interface and backend processing pipeline.
Speaker: Swati Sharma
What is needed to integrate an accessibility bar (text‑to‑speech, screen‑reader support) into the translation plugin?
Adding built‑in accessibility features would broaden inclusivity, yet demands research into compatible APIs, performance impact, and compliance with accessibility standards.
Speaker: Swati Sharma
What are the best practices for efficiently translating dynamic content without overwhelming API calls or degrading response time?
Dynamic sites generate frequent content changes; optimizing batching, caching, and request throttling is essential for scalable real‑time translation.
Speaker: Swati Sharma
How can the plugin reliably detect and skip translation of mixed‑language or already‑translated segments within a page?
Accurate language detection in mixed content prevents over‑translation and preserves intended meaning, requiring advanced detection algorithms.
Speaker: Swati Sharma
What steps are required to ensure DBM (Digital Brand Management) compliance across diverse website frameworks when integrating the plugin?
Understanding and implementing DBM compliance is crucial for government portals and may involve additional validation, testing, and documentation.
Speaker: Shailendra Pal Singh

Disclaimer: This is not an official session record. DiploAI generates these resources from audiovisual recordings, and they are presented as-is, including potential errors. Due to logistical challenges, such as discrepancies in audio/video or transcripts, names may be misspelled. We strive for accuracy to the best of our ability.