Text to speech · संस्कृतम्
Pāṇini TTS reads Sanskrit in Devanagari with a native Sanskrit voice, for learning, recitation and spoken-Sanskrit content.
पूजायाः booking श्वः प्रातः सप्तवादने निश्चिता अस्ति। कृपया पञ्चदश निमेषान् पूर्वम् आगच्छतु, सम्पूर्णं विवरणं SMS द्वारा प्रेषितम् अस्ति।
Voices
Free to play in your browser without an account, up to 220 characters at a time. To save the audio as a file, sign up free for 10,000 characters and one voice clone, no card required: the dashboard saves WAV and the API returns MP3.
Making a video? See AI voice-over for YouTube and Reels. The audio is yours to use on monetised channels.
Last verified 24 October 2026
Saanvi, a native Sanskrit platform voice, reads the playground above. Any Sonex Labs voice can also read Sanskrit, keeping its own accent, and a voice cloned from a 10-second recording of a Sanskrit speaker carries that speaker's accent.
Sign up free, then send Sanskrit text to the API with "output_format": "mp3" and save the file, or generate clips in the dashboard and download them. Scripts longer than the playground's 220 characters work the same way.
About Sanskrit
Sanskrit is read almost exactly as it is written, which makes small marks matter. The visarga in नमः carries a faint echo of the vowel before it, the anusvara changes with the consonant that follows, and sandhi joins words so that a sentence can look like one long word. A reader that treats Sanskrit as Hindi drops the short a that Sanskrit keeps at the end of words like राम and देव, and blurs these sounds. The samples on this page are read by Saanvi, a native Sanskrit platform voice.
Most Sanskrit people hear today is either chanted or spoken in the simple conversational style taught in spoken-Sanskrit classes, as in "भवान् कथम् अस्ति?". The samples use that spoken style, because that is what learners and listeners of Sanskrit radio and video are used to, but they avoid भवान् and भवती, the polite "you", because those mark the listener as a man or a woman.
Use cases
Pronunciation models for students, read clearly from the same text they study.
Spoken readings of verses and texts for apps, audiobooks and temple and cultural content.
Narration for news, stories and explainers in conversational Sanskrit.
Commercial use
The full wording is in our terms of service.
YouTube
Yes, AI voices are allowed. What YouTube limits is mass-produced, repetitive content: videos made from a template with little original work. Its July 2025 update renamed that rule from “repetitious” to “inauthentic” content (YouTube’s monetisation policies).
Write your own script, add your own research or editing, and keep one consistent voice for the channel. Where a realistic AI voice could mislead viewers, use YouTube’s altered or synthetic content label. The monetisation decision is always YouTube’s.
Voice cloning
Clone your voice from a 10-second recording. Your clone speaks Sanskrit, and every other language Pāṇini supports, in your own voice. The language comes from the text you type, so a clone recorded in English or Hindi can read a Sanskrit script.
Your accent comes with it: a clone sounds like you speaking Sanskrit, not like a different native speaker. Every free account includes one voice clone. Clone only your own voice, or a voice whose owner has agreed.
API
One request returns Sanskrit audio as MP3. The language is detected from the text, so no language setting is needed. Pāṇini TTS starts streaming audio in under 200 ms (time to first byte).
1curl https://api.sonexlabs.com/v1/speech \2 --header 'Authorization: Bearer YOUR_API_KEY' \3 --header 'Content-Type: application/json' \4 --data '{"text": "पूजायाः booking श्वः प्रातः सप्तवादने निश्चिता अस्ति। कृपया पञ्चदश निमेषान् पूर्वम् आगच्छतु, सम्पूर्णं विवरणं SMS द्वारा प्रेषितम् अस्ति।", "output_format": "mp3"}' \5 --output sanskrit.mp3FAQ
Yes. The playground on this page reads up to 220 characters of Sanskrit at a time with no account. Sign up free for 10,000 characters and one voice clone, no card; after that it costs $0.03125 per 1,000 characters.
Yes, after free sign-up. The playground on this page plays audio in your browser only, up to 220 characters at a time, so you can check the voice first. Sign up free (10,000 characters and one voice clone, no card): the dashboard saves each clip as a WAV file with Download audio, and the API returns MP3 when you set "output_format": "mp3".
Yes. Saanvi is a native Sanskrit platform voice and reads every sample on this page. You can also clone a voice from a 10-second sample.
It reads them as written in Devanagari. Write the text with the sandhi you want spoken.
Pāṇini reads Sanskrit in a spoken style. For accented Vedic recitation, test a sample before relying on it.
$0.03125 per 1,000 characters, the same as every language.
Yes. Audio you generate, on the free tier or with paid credits, can be used on monetised YouTube channels, Shorts, Reels and in ads, with no attribution. YouTube limits mass-produced, repetitive videos, not AI voices, so write your own script and keep your edits original. The monetisation decision is YouTube's.
The audio you generate is yours to use, including commercially, with no attribution and no royalties to Sonex Labs. You are responsible for the script itself: if you read someone else's text, you need their permission.
Yes. A Sonex voice clone is not tied to the language it was recorded in. Type a Sanskrit script and your clone reads it in your own voice, with Sanskrit pronunciation. Your natural accent carries over, so it sounds like you speaking Sanskrit.
More languages
See text to speech in every language, the full list of 250+ languages, pricing, the Pāṇini TTS API, or transcribe Sanskrit audio with Valmiki speech to text.
10,000 free text-to-speech characters and one free voice clone that speaks every language, no card required. Every language is billed at the same rate.