Text to speech · සිංහල
Pāṇini TTS reads Sinhala in its own script and in the spoken style Sri Lankans use on calls, including the English words they mix into nearly every sentence.
ඔයාගේ appointment එක ලබන අඟහරුවාදා උදේ දහයට confirm කළා, ඩොක්ටර්ගේ ගාස්තුව රුපියල් තුන්දාහයි. දවසකට කලින් SMS එකක් එනවා, වෙලාව වෙනස් කරන්න ඕන නම් අපිට call එකක් දෙන්න.
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
There is no native Sinhala platform voice yet, so the playground uses Priya, a voice recorded in another language: the Sinhala text is read correctly, in that voice's accent. For a local accent, clone a native Sinhala speaker from a 10-second recording and use that voice for every clip.
Sign up free, then send Sinhala 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 Sinhala
Sinhala has its own rounded script, an abugida descended from Brahmi: each consonant carries a built-in vowel that is changed with signs such as ා and ි, and the sign ් removes it. Sinhala is also strongly diglossic. Written Sinhala uses verb endings nobody uses in conversation, so a notice may say මම යමි for "I go" where a speaker says මම යනවා. A reminder written in the literary style sounds stiff and distant when read aloud on a call.
Everyday Sinhala, especially in business, is full of English: bill, payment, account, reload, and booking a doctor in Sri Lanka is "channelling", written චැනලිං. Greetings run from the formal ආයුබෝවන් ("may you live long") to a casual හලෝ. Banks, telecom operators and private hospitals in Sri Lanka handle callers who switch between Sinhala and English mid-sentence, and many Sri Lankans work in the Gulf, where employers, recruiters and remittance services need to reach them and their families at home.
Use cases
Doctor appointment confirmations and reminders for private hospitals and channelling centres in Sri Lanka.
Bill, reload, card and loan calls for customers who mix Sinhala and English.
Remittance, recruitment and welfare calls for Sri Lankan workers in the Gulf and their families at home.
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 Sinhala, 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 Sinhala script.
Your accent comes with it: a clone sounds like you speaking Sinhala, 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 Sinhala 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": "ඔයාගේ appointment එක ලබන අඟහරුවාදා උදේ දහයට confirm කළා, ඩොක්ටර්ගේ ගාස්තුව රුපියල් තුන්දාහයි. දවසකට කලින් SMS එකක් එනවා, වෙලාව වෙනස් කරන්න ඕන නම් අපිට call එකක් දෙන්න.", "output_format": "mp3"}' \5 --output sinhala.mp3FAQ
Yes. The playground on this page reads up to 220 characters of Sinhala 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. It reads whichever style you write; for calls, spoken forms such as යනවා sound far more natural than literary ones.
Yes. English words, in Latin letters or in Sinhala script, are read inside Sinhala sentences in the same voice.
Priya reads these samples; any Sonex Labs voice can speak Sinhala, and you can clone a native speaker's voice from 10 seconds.
$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 Sinhala script and your clone reads it in your own voice, with Sinhala pronunciation. Your natural accent carries over, so it sounds like you speaking Sinhala.
More languages
See text to speech in every language, the full list of 250+ languages, pricing, the Pāṇini TTS API, or transcribe Sinhala 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.