Rendered at 11:05:38 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
lordleft 1 days ago [-]
Forgive my ignorance; I'm not a Sanskrit speaker (Malayalam is my first language) -- but I love the sound of Sanskrit.
I have lots of questions: what's the use case for this? Primarily religious / liturgical? It also seems that the fact that this tool works means that any arbitrary Sanskrit sentence can be translated into a chant by some sort of procedure (dare I say algorithm)? I'm terribly curious and fascinated by this!
devsda 1 days ago [-]
I think complex Sanskrit words are difficult to roll off the tongue and pronounce if read in a dry manner specially if you don't already know the words or meaning, which unfortunately is true for the majority out there who want to read them, including myself.
Having a spoken reference that too as a chant makes it easy to recite the verses.
shash 1 days ago [-]
Learning and figuring out the meter and rhythm of a new passage? If you don’t have someone who knows to chant it for you…
Besides, it’s a fun exercise, so why not?
throwawaysjskdk 1 days ago [-]
Everything doesn’t need a use case. It’s simply cool.
Automating pundits in family functions would be my first guess. Could be more convenient and reliable than having to invite some stranger just for recitation.
tinuviel 1 days ago [-]
You should ask yourself - would most christians prefer baptism in a bathtubs at home or drive in weddings for convenience? No? Exactly.
Hindu Vedic pandits and priests who come in and run priestly events and functions at Hindu homes are usually well known within their communities are not treated as strangers and neither is there an element of inconvenience. If anything their absence adds an element of inconvenience. For one most rituals in sanskrit are available on youtube for those who want to diy. But most discerning Hindus prefer the real thing. Same as Christians.
aprilthird2021 21 hours ago [-]
Come on be so for real right now? I have been to many Hindu events, and the pandit is really just there to make things official and say the words. 90% of attendees don't know what he's actually saying. 80% have never met him or his associates.
Now you can't automate him either. His presence is there because religious rituals and practice and tradition mandate his presence, but if you could just play the chants over a speaker and have people understand and follow the ritual instructions some other way, nothing would really change.
For what it's worth, people can and do use AI visuals and sermons in Christianity as well
redsocksfan45 21 hours ago [-]
[dead]
sebmellen 1 days ago [-]
This must be insanely difficult to get right. I was not expecting such an impressive result from a site that looks so vibe coded! The look is underselling how good this is.
ks2048 1 days ago [-]
I was put off by the vibed-design, but everything looks well done and well-explained.
From what I can tell, it used 5.3 hours of single voice fine-tune data.
aitchnyu 20 hours ago [-]
Looks perfectly functional and clear to the eyes for me. They also included a warning to not background/unfocus the tab on a mobile device so that our generation job (on the cloud AFAICT) doesnt get cancelled.
woozlewuzzle 1 days ago [-]
I'm curious what exactly makes this vibe-coded?
I've noticed a lot of people seem quick to dismiss something as vibe-coded these days.
waonderer 19 hours ago [-]
The font, the colors, and the design is so similar to what an LLM will choose.
This is most likely done by claude as per the aesthetics. Every AI has its own aesthetics as well.
amunozo 1 days ago [-]
I think they mean that the visual design of the site is vibe coded, as most LLMs use this style while making web pages.
ks2048 1 days ago [-]
It was based on an existing TTS, IndicT5. I wonder how different is “Sanskrit Chanting” to languages it could already do, like Hindi. Is it largely the glyph—to-phoneme that needs relearning? Or pitch control? Or more?
sieve 1 days ago [-]
The biggest problem with a lot of northern languages is the awful schwa deletion. Even the Marathi of Maharashtra is subject to it. Strangely, the Marathi of Thanjavur has far, far less of it from what little I have heard of it.
Sanskrit does not do schwa deletion. So engines must map the phonemes to Kannada/Telugu (which support the full complement of Sanskrit sounds) if they want to get somewhere. A lot of this can be solved if the backend supports ipa.
But this is for classical Sanskrit. Vedic recitation is too complex (and I know too little about it) to handle without a LOT of work.
delta_p_delta_x 1 days ago [-]
It's pretty funny reading comments on social media by north Indians whenever something on Sanskrit is posted. 'It's Ram, not Rama, it's yog, not yoga'... And they have no idea what schwa deletion is.
ashishb 1 days ago [-]
> It's Ram, not Rama, it's yog, not yoga'... And they have no idea what schwa deletion is.
It is neither.
The fundamental issue is that there is no way to represent the schwa sound in English[1].
All of a,e,i,o,u have been used to communicate the schwa (or schwa-like) sound in English.
- The `a` in about
- The `e` in taken
- The `i` in cousin
- The `o` in button
- The `u` in upon
I wouldn't say 'neither', because by your own example, 'a' in English can represent ⟨ə⟩. That every other vowel letter also can is English's low level of phoneticism with respect to the script it uses. Many other languages using the Latin script (German, Italian, Finnish) don't have this problem, what you see is what get.
Oddly enough amongst the Indic languages, Tamil has precisely the same problem: க, ப, ட may be voiced or voiceless plosives depending on context. Sanskrit loanwords in Tamil are typically pronounced very differently compared to their original in Sanskrit, or even in Telugu.
Personally when transliterating any Indic language I tend to use ISO-15919, and in that scheme, it is Rāma, and 'a' represents the schwa. Or Rāmaḥ, Rāmam, Rāmē, or Rāmasya, whichever grammatical attachment is appropriate.
ashishb 1 days ago [-]
> That every other vowel letter also can is English's low level of phoneticism
The level of phoneticism between English language and its latin script is not evenly spread.
For example, the letter "c" might mean /s/ or /k/ sound.
However, the letter "k" almost certainly means /k/ sound.
In some ways, the schwa sound in English the worst as there is no symbol which is committed even partially towards it.
> it is Rāma, and 'a' represents the schwa.
Sure, but if my name is Rāma, I have to choose either "Ram" or "Rama" or "Raama" for my passport name.
Or legal name in most places, non-alphabetic symbols do not work with all modern systems.
> Many other languages using the Latin script (German, Italian, Finnish) don't have this problem, what you see is what get.
English imports spellings from other cultures and adds its own layer of pronunciations.
Other languages probably don't do it as often.
delta_p_delta_x 1 days ago [-]
> In some ways, the schwa sound in English the worst as there is no symbol which is committed even partially towards it.
> English imports spellings from other cultures and adds its own layer of pronunciations. Other languages probably don't do it as often.
English is almost unique in how inconsistent its orthography is especially with respect to vowel sounds, and loanwords are only the latest manifestation of this problem. Even consonants aren't spared. Consider the digraph 'th'. This can be a voiced or voiceless dental fricatives. English used to have letters for each: ð and þ. 'ough' has nine pronunciations—plough, though, through, thorough, cough, rough, bought, lough, hiccough.
English has experienced contact with such a wide variety of unrelated foreign languages to an extent few others ever have.
rramadass 1 days ago [-]
Wikipedia has an interesting page on "Brahmin Tamil" which is the Tamil dialect spoken by Brahmins in Tamil Nadu and consists of Classical Tamil with a lot of Sanskrit influence - https://en.wikipedia.org/wiki/Brahmin_Tamil
prox 1 days ago [-]
Luckily a lot of research has gone into Vedic recitation from an academic perspective if someone would take up the mantle.
sophrosyne42 1 days ago [-]
There are sounds in sanskrit that don't exist in Hindi, including vocalizations that exist in Sanskrit which are omitted in Hindi for the same glyphs. Additionally, Sanskrit meter has pretty specific rules on which should be stressed and unstressed, when to have pitch changes, and the length of each sound.
graphcolorer 1 days ago [-]
Interestingly, the paper says that the glyph to phoneme conversion is lossy for Hindi (Devanagari) script due to schwa deletion, so one of the key innovations here is that the Sanskrit is first transliterated into Kannada before TTS.
ultrasounder 1 days ago [-]
Very nice implementation. I tried developing my own to practice Santhai(repeat thrice) to learn Upnishads and this tool would be at the center of my workflow. A locally installable version would be even great! Kudos. Dhanyosmi :-)
Interestingly, the word ब्रह्मा which should say Brahmaaaa says baa.
Please take a look.
woadwarrior01 1 days ago [-]
BaaS: Bhatta as a Service.
nb: Bhatta is Sanskrit for priest.
never_inline 1 days ago [-]
Why does the visarga "echo" at the end of the verse? A mixed IAST - HK transliteration on the front page like "Bhāgavata-VāNi" does not inspire confidence either. Is it vibed?
xerosanyam 1 days ago [-]
Even if it was vibe-coded, does that matter? The result is solid. If it’s not to your taste, wait for the next release.
rramadass 1 days ago [-]
People seem to be making all sorts of assumptions/conjectures about the project and confusing themselves without reading the paper explaining the project (linked to in the site itself);
From the introduction;
Classical Sanskrit recitation, parāyaṇa, is a chanted rather than a read register. A faithful synthesizer must hold long vowels, sustain a terminal visarga, articulate retroflex and aspirated consonants, render dense consonant conjuncts cleanly, and respect the metrical structure of the verse.
None of these is well served by general-purpose text-to-speech, and there is essentially no chant-domain training data available off the shelf. The problem is therefore doubly hard: it is low-resource, and the target prosody is a specialized melodic contour rather than ordinary read speech.
This report describes a system, Vāgdhenu, that solves the practical version of this problem well enough to ship two large deployments, and it documents the design decisions, the dead ends, and the one negative result that turned out to be the most useful finding. We do not claim a new model. We claim an honest account of what it takes to build a faithful Sanskrit chant pipeline on top of current open backbones, what works, and what is architecturally out of reach.
Our framing is that of an experience report. The evidence we offer is the comparative lineage across architecture families, a reproducible production system, two shipped artifacts at real scale, and a public release of code, weights, data, and a live demonstration. Formal listening studies are limited to expert evaluation, which we state plainly and treat as a limitation rather than a result.
vishnugupta 1 days ago [-]
Perhaps you could edit the submission to add this context?
rramadass 1 days ago [-]
Sorry, am not the submitter so we will let it be.
6 days ago [-]
nopin 1 days ago [-]
This is so so so cool. the UX of the app could be better.
bhargav 1 days ago [-]
Amazing tool and very accurate, even on some esoteric texts I tested. Wish it let me just dump an entire stotra :)
febed 1 days ago [-]
Would be interesting to make a similar one for Tibetan chants.
katspaugh 1 days ago [-]
Can the same engine be extended to Pali for Buddhist suttas?
porridgeraisin 1 days ago [-]
Yes. The dhammapada uses a lot of Anushthubh chandas, which is an option in the website. However, the language differences between pali and sanskrit are enough to make TTS trip up. E.g only one "s" variant, and karma -> kamma, etc,. If you finetuned on pali a little bit it should work fine.
orsenthil 1 days ago [-]
This is Excellent!
xerosanyam 1 days ago [-]
love it!
_alternator_ 1 days ago [-]
[dead]
girishr 1 days ago [-]
[dead]
zkmon 1 days ago [-]
The TTS quality seems to be poor. I just entered a single word "jaganmaatham" and it failed to pronounce it.
What's the point anyway? If you really love your traditions, slokas and chanting, please keep it as natural as possible, instead of plasticizing it to the core.
This is third level of mechanizing the sacred rituals. First - we lost the live chanting due to recorded recitals with human voice. Then we lost the experience of presence due to online streaming. And now even human voice is lost - the broken chanting is generated. So, combined all together, you have a streaming of the rituals which was performed by recorded chanting that never really involved a human reading the sloka.
Just because we can pollute the world, we need not do it.
Arun2009 1 days ago [-]
> First - we lost the live chanting due to recorded recitals with human voice. Then we lost the experience of presence due to online streaming. And now even human voice is lost - the broken chanting is generated.
This is not true at all. Live chanting, live pUjAs, etc. are still very much practiced. It's just that recorded versions also became available, making our lives richer.
The same applies to other art forms. E.g., bharatanATyam is still performed live, but we also have recorded performances. That is a good thing!
totetsu 1 days ago [-]
Seems like its point is to help people practice themselves.
> Vāgbodhinī
A Sanskrit chant tutor. Paste any śloka (or prose) in any script, hear its metre-aware reference chant rendered by Vāgdhenu, then chant along — a Sanskrit speech model scores every syllable and shows you what to fix. For classical (laukika) Sanskrit.
zkmon 1 days ago [-]
That's how they will present it. But the direction is clear. It can replace a human chanting professional. If it can, it will. The future is not far off where an AI bot will interact with the users, asking their family name etc and weave it into the chanting.
devsda 1 days ago [-]
I have tried the word you mentioned along with few other words together and there were no issues.
It doesn't have to be a replacement. Anyone who has ever been in the physical presence of an expert reciting sanskrit verses knows that this can never replace that experience.
It will only make the language and the chants more accessible.
zkmon 1 days ago [-]
> I have tried the word you mentioned along with few other words together and there were no issues.
I have typed the word in English literals, and it made a horrible pronunciation of the word.
> It will only make the language and the chants more accessible.
No, it will turn sacred chanting into an AI slop. Entirely due to desire of people wishing to make some quick bucks or cheap reputation.
rramadass 1 days ago [-]
The frontend accepts Sanskrit and other Indic Language scripts but not made for English and hence your result; GIGO principle.
I tried out the Gayathri Manthra (a simple test) using Sanskrit, Tamil and English scripts and as expected, the first two render fine but not the last.
rramadass 1 days ago [-]
Yours is a very shortsighted and myopic view on the importance of using modern technology in order to maintain/enhance/propagate ancient cultural/linguistic knowledge which is losing its appeal in the "common populace".
This is another tool to help correct that balance.
You don't need to know about the person, to understand what is done here. This is no invention or profound deed. Anyone using the open-weights TTS models can do this. Talk about the overall goal.
rramadass 1 days ago [-]
You do need to know about a person to understand why he did a project that he did. What were his motivations and goals? That is the point here which can be inferred from his bio/talks.
His goals need not be what you want them to be; his project; his rules.
Nobody is claiming this is something earth-shattering; just that it is an interesting project on a difficult subject matter. The author has linked to the paper for the project on the site itself which you can read for your edification.
From the introduction;
Classical Sanskrit recitation, parāyaṇa, is a chanted rather than a read register. A faithful synthesizer must hold long vowels, sustain a terminal visarga, articulate retroflex and aspirated consonants, render dense consonant conjuncts cleanly, and respect the metrical structure of the verse.
None of these is well served by general-purpose text-to-speech, and there is essentially no chant-domain training data available off the shelf. The problem is therefore doubly hard: it is low-resource, and the target prosody is a specialized melodic contour rather than ordinary read speech.
This report describes a system, Vāgdhenu, that solves the practical version of this problem well enough to ship two large deployments, and it documents the design decisions, the dead ends, and the one negative result that turned out to be the most useful finding. We do not claim a new
model. We claim an honest account of what it takes to build a faithful Sanskrit chant pipeline on top of current open backbones, what works, and what is architecturally out of reach.
Our framing is that of an experience report. The evidence we offer is the comparative lineage
across architecture families, a reproducible production system, two shipped artifacts at real scale,
and a public release of code, weights, data, and a live demonstration. Formal listening studies are
limited to expert evaluation, which we state plainly and treat as a limitation rather than a result.
As a practical example; if you have ever heard even the common Gayathri Mantra being chanted by a Tamil Thanjavur Brahmin priest vs. a UP Allahabad Brahmin priest you would know the wide difference in utterances. Having something like this gives you a reference (albeit with a South Indian Kannada bent) to compare against.
zkmon 10 hours ago [-]
> His goals need not be what you want them to be; his project; his rules.
Do not post on HN if the goals/rules/project are not be questioned. This is not a bhajan forum.
> You do need to know about a person to understand why he did a project that he did. What were his motivations and goals? That is the point here which can be inferred from his bio/talks.
If your approach to assess something is only by learning about the person, and not by what they did or said then you need to know about me as well. But you came to conclusions without knowing about me, which violates your own principle.
Also, if you think it is blasphemous to question the work done by your great person, please do not post it here. I'm not into "person-worshipping" or andh-bhakt cult. And this is not a thread to discuss about the person. The post talks about the work and my comments are in that context. I'm not required to get into bio/talks/profile or the perceived greatness of a person.
rramadass 7 hours ago [-]
> Do not post on HN if the goals/rules/project are not be questioned.
Who said they cannot be questioned? But the author/submitter is not obligated to anticipate/satisfy/answer any of your questions/assumptions/etc. Something is posted on its own terms and you take it or leave it with/without criticism. Everything is volitional.
> If your approach to assess something is only by learning about the person, and not by what they did or said then you need to know about me as well. But you came to conclusions without knowing about me, which violates your own principle.
Learning about a person behind some work is one factor but not the only factor. In this case it was relevant since the author is both a AI researcher and a Sanskrit scholar and so the motivations/goals are easily inferred.
If you want people to know about you (presumably w.r.t. to your scholarship in this domain) then you should have something in your profile instead of being anonymous and/or made it explicit in your comment. In its absence, people can't imagine things.
Using talking points like "bhajan forum", "person-worshipping", "andh-bhakt cult" etc. is simply you projecting your assumptions/biases and nothing more. Pointing to a person's background has to do with establishing domain expertise and technical credentials.
You can post any comment you want but so can others on your comment whether you like it or not. People can dismiss you the way you dismiss others.
dartharva 1 days ago [-]
>If you really love your traditions, slokas and chanting
Most people don't. Slokas and chanting are just traditions we do begrudgingly to enable the actual social objectives (family bonding, etc) of the rituals; you'd be hard-pressed to find anyone who actually understands them, even if they have it memorized by heart. I'd say automating the recitation would be quite a good sell for most families, it gives a more convenient and reliable option in place of having to invite strangers over (and reinforcing caste roles) just for that.
I have lots of questions: what's the use case for this? Primarily religious / liturgical? It also seems that the fact that this tool works means that any arbitrary Sanskrit sentence can be translated into a chant by some sort of procedure (dare I say algorithm)? I'm terribly curious and fascinated by this!
Having a spoken reference that too as a chant makes it easy to recite the verses.
Besides, it’s a fun exercise, so why not?
Hindu Vedic pandits and priests who come in and run priestly events and functions at Hindu homes are usually well known within their communities are not treated as strangers and neither is there an element of inconvenience. If anything their absence adds an element of inconvenience. For one most rituals in sanskrit are available on youtube for those who want to diy. But most discerning Hindus prefer the real thing. Same as Christians.
Now you can't automate him either. His presence is there because religious rituals and practice and tradition mandate his presence, but if you could just play the chants over a speaker and have people understand and follow the ritual instructions some other way, nothing would really change.
For what it's worth, people can and do use AI visuals and sermons in Christianity as well
From what I can tell, it used 5.3 hours of single voice fine-tune data.
I've noticed a lot of people seem quick to dismiss something as vibe-coded these days.
This is most likely done by claude as per the aesthetics. Every AI has its own aesthetics as well.
Sanskrit does not do schwa deletion. So engines must map the phonemes to Kannada/Telugu (which support the full complement of Sanskrit sounds) if they want to get somewhere. A lot of this can be solved if the backend supports ipa.
But this is for classical Sanskrit. Vedic recitation is too complex (and I know too little about it) to handle without a LOT of work.
It is neither.
The fundamental issue is that there is no way to represent the schwa sound in English[1]. All of a,e,i,o,u have been used to communicate the schwa (or schwa-like) sound in English.
1 - https://ashishb.net/linguistics/schwa/Oddly enough amongst the Indic languages, Tamil has precisely the same problem: க, ப, ட may be voiced or voiceless plosives depending on context. Sanskrit loanwords in Tamil are typically pronounced very differently compared to their original in Sanskrit, or even in Telugu.
Personally when transliterating any Indic language I tend to use ISO-15919, and in that scheme, it is Rāma, and 'a' represents the schwa. Or Rāmaḥ, Rāmam, Rāmē, or Rāmasya, whichever grammatical attachment is appropriate.
The level of phoneticism between English language and its latin script is not evenly spread.
For example, the letter "c" might mean /s/ or /k/ sound. However, the letter "k" almost certainly means /k/ sound.
In some ways, the schwa sound in English the worst as there is no symbol which is committed even partially towards it.
> it is Rāma, and 'a' represents the schwa.
Sure, but if my name is Rāma, I have to choose either "Ram" or "Rama" or "Raama" for my passport name. Or legal name in most places, non-alphabetic symbols do not work with all modern systems.
> Many other languages using the Latin script (German, Italian, Finnish) don't have this problem, what you see is what get.
English imports spellings from other cultures and adds its own layer of pronunciations. Other languages probably don't do it as often.
> English imports spellings from other cultures and adds its own layer of pronunciations. Other languages probably don't do it as often.
English is almost unique in how inconsistent its orthography is especially with respect to vowel sounds, and loanwords are only the latest manifestation of this problem. Even consonants aren't spared. Consider the digraph 'th'. This can be a voiced or voiceless dental fricatives. English used to have letters for each: ð and þ. 'ough' has nine pronunciations—plough, though, through, thorough, cough, rough, bought, lough, hiccough.
English has experienced contact with such a wide variety of unrelated foreign languages to an extent few others ever have.
I just tried this
यं ब्रह्मा वरुणेन्द्ररुद्रमरुत: स्तुन्वन्ति दिव्यै: स्तवै-
र्वेदै: साङ्गपदक्रमोपनिषदैर्गायन्ति यं सामगा: ।
ध्यानावस्थिततद्गतेन मनसा पश्यन्ति यं योगिनो
यस्यान्तं न विदु: सुरासुरगणा देवाय तस्मै नम: ॥
Interestingly, the word ब्रह्मा which should say Brahmaaaa says baa. Please take a look.
nb: Bhatta is Sanskrit for priest.
From the introduction;
Classical Sanskrit recitation, parāyaṇa, is a chanted rather than a read register. A faithful synthesizer must hold long vowels, sustain a terminal visarga, articulate retroflex and aspirated consonants, render dense consonant conjuncts cleanly, and respect the metrical structure of the verse.
None of these is well served by general-purpose text-to-speech, and there is essentially no chant-domain training data available off the shelf. The problem is therefore doubly hard: it is low-resource, and the target prosody is a specialized melodic contour rather than ordinary read speech.
This report describes a system, Vāgdhenu, that solves the practical version of this problem well enough to ship two large deployments, and it documents the design decisions, the dead ends, and the one negative result that turned out to be the most useful finding. We do not claim a new model. We claim an honest account of what it takes to build a faithful Sanskrit chant pipeline on top of current open backbones, what works, and what is architecturally out of reach.
Our framing is that of an experience report. The evidence we offer is the comparative lineage across architecture families, a reproducible production system, two shipped artifacts at real scale, and a public release of code, weights, data, and a live demonstration. Formal listening studies are limited to expert evaluation, which we state plainly and treat as a limitation rather than a result.
What's the point anyway? If you really love your traditions, slokas and chanting, please keep it as natural as possible, instead of plasticizing it to the core.
This is third level of mechanizing the sacred rituals. First - we lost the live chanting due to recorded recitals with human voice. Then we lost the experience of presence due to online streaming. And now even human voice is lost - the broken chanting is generated. So, combined all together, you have a streaming of the rituals which was performed by recorded chanting that never really involved a human reading the sloka.
Just because we can pollute the world, we need not do it.
This is not true at all. Live chanting, live pUjAs, etc. are still very much practiced. It's just that recorded versions also became available, making our lives richer.
The same applies to other art forms. E.g., bharatanATyam is still performed live, but we also have recorded performances. That is a good thing!
> Vāgbodhinī A Sanskrit chant tutor. Paste any śloka (or prose) in any script, hear its metre-aware reference chant rendered by Vāgdhenu, then chant along — a Sanskrit speech model scores every syllable and shows you what to fix. For classical (laukika) Sanskrit.
It doesn't have to be a replacement. Anyone who has ever been in the physical presence of an expert reciting sanskrit verses knows that this can never replace that experience.
It will only make the language and the chants more accessible.
I have typed the word in English literals, and it made a horrible pronunciation of the word.
> It will only make the language and the chants more accessible.
No, it will turn sacred chanting into an AI slop. Entirely due to desire of people wishing to make some quick bucks or cheap reputation.
I tried out the Gayathri Manthra (a simple test) using Sanskrit, Tamil and English scripts and as expected, the first two render fine but not the last.
This is another tool to help correct that balance.
The author seems a pretty knowledgeable person - https://prathosh.in/
His talk "The Non-negotiability of Shastra-s in Modern Science" - https://www.youtube.com/watch?v=i5Tp4gdQiTM
His goals need not be what you want them to be; his project; his rules.
Nobody is claiming this is something earth-shattering; just that it is an interesting project on a difficult subject matter. The author has linked to the paper for the project on the site itself which you can read for your edification.
From the introduction;
Classical Sanskrit recitation, parāyaṇa, is a chanted rather than a read register. A faithful synthesizer must hold long vowels, sustain a terminal visarga, articulate retroflex and aspirated consonants, render dense consonant conjuncts cleanly, and respect the metrical structure of the verse.
None of these is well served by general-purpose text-to-speech, and there is essentially no chant-domain training data available off the shelf. The problem is therefore doubly hard: it is low-resource, and the target prosody is a specialized melodic contour rather than ordinary read speech.
This report describes a system, Vāgdhenu, that solves the practical version of this problem well enough to ship two large deployments, and it documents the design decisions, the dead ends, and the one negative result that turned out to be the most useful finding. We do not claim a new model. We claim an honest account of what it takes to build a faithful Sanskrit chant pipeline on top of current open backbones, what works, and what is architecturally out of reach.
Our framing is that of an experience report. The evidence we offer is the comparative lineage across architecture families, a reproducible production system, two shipped artifacts at real scale, and a public release of code, weights, data, and a live demonstration. Formal listening studies are limited to expert evaluation, which we state plainly and treat as a limitation rather than a result.
As a practical example; if you have ever heard even the common Gayathri Mantra being chanted by a Tamil Thanjavur Brahmin priest vs. a UP Allahabad Brahmin priest you would know the wide difference in utterances. Having something like this gives you a reference (albeit with a South Indian Kannada bent) to compare against.
Do not post on HN if the goals/rules/project are not be questioned. This is not a bhajan forum.
> You do need to know about a person to understand why he did a project that he did. What were his motivations and goals? That is the point here which can be inferred from his bio/talks.
If your approach to assess something is only by learning about the person, and not by what they did or said then you need to know about me as well. But you came to conclusions without knowing about me, which violates your own principle.
Also, if you think it is blasphemous to question the work done by your great person, please do not post it here. I'm not into "person-worshipping" or andh-bhakt cult. And this is not a thread to discuss about the person. The post talks about the work and my comments are in that context. I'm not required to get into bio/talks/profile or the perceived greatness of a person.
Who said they cannot be questioned? But the author/submitter is not obligated to anticipate/satisfy/answer any of your questions/assumptions/etc. Something is posted on its own terms and you take it or leave it with/without criticism. Everything is volitional.
In this context this recent cnn article "‘Whataboutism’ makes the internet exhausting. Why people think this way" (Bean Soup Theory) is very relevant - https://edition.cnn.com/2026/07/16/health/bean-soup-theory-s...
> If your approach to assess something is only by learning about the person, and not by what they did or said then you need to know about me as well. But you came to conclusions without knowing about me, which violates your own principle.
Learning about a person behind some work is one factor but not the only factor. In this case it was relevant since the author is both a AI researcher and a Sanskrit scholar and so the motivations/goals are easily inferred.
If you want people to know about you (presumably w.r.t. to your scholarship in this domain) then you should have something in your profile instead of being anonymous and/or made it explicit in your comment. In its absence, people can't imagine things.
Using talking points like "bhajan forum", "person-worshipping", "andh-bhakt cult" etc. is simply you projecting your assumptions/biases and nothing more. Pointing to a person's background has to do with establishing domain expertise and technical credentials.
You can post any comment you want but so can others on your comment whether you like it or not. People can dismiss you the way you dismiss others.
Most people don't. Slokas and chanting are just traditions we do begrudgingly to enable the actual social objectives (family bonding, etc) of the rituals; you'd be hard-pressed to find anyone who actually understands them, even if they have it memorized by heart. I'd say automating the recitation would be quite a good sell for most families, it gives a more convenient and reliable option in place of having to invite strangers over (and reinforcing caste roles) just for that.