Text to speech · سرائیکی
Pāṇini TTS reads Saraiki written in Perso-Arabic script, for calls and content aimed at southern Punjab and Saraiki speakers abroad.
اساں Sonex توں ڳالھ کریندے پئے ہاں، تہاݙا order سبھاݨ ݙینہہ دے 2 توں 4 وجے دے وچ delivery تھیسی۔ گھر نہ ہوو تاں SMS آلے link تے ٻیا ویلا چُݨ گھنو۔
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 Saraiki platform voice yet, so the playground uses Alok, a voice recorded in another language: the Saraiki text is read correctly, in that voice's accent. For a local accent, clone a native Saraiki speaker from a 10-second recording and use that voice for every clip.
Sign up free, then send Saraiki 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 Saraiki
Saraiki is the language of Multan and Bahawalpur, mostly spoken in Pakistan. It is written in Perso-Arabic script with letters of its own for its implosive sounds, such as ٻ, ڄ, ݙ and ڳ, which Urdu and Punjabi do not use. Its everyday speech is soft and polite: سئیں ("sain", a respectful "sir"), میݙا ("my"), تساں ("you", respectful) and ونڄݨ ("to go") are words a Saraiki listener expects, and an Urdu or Punjabi voice gets them wrong.
There is no dedicated Saraiki platform voice yet. The samples on this page are read by Alok, a Hindi voice, from Saraiki text. In India, Saraiki survives mainly in Partition-era families, where it is often called Multani and is now spoken mostly by older people, so a message in Saraiki means something to them. For the most local sound, clone a voice from a 10-second recording of a Saraiki speaker; the clone then reads Saraiki in that speaker's own accent.
Use cases
Loan, EMI and account calls for customers in southern Punjab who are more at ease in Saraiki than Urdu.
Crop, weather and payment calls for cotton and wheat farmers in the Saraiki belt.
Narration for Saraiki poetry, Sufi music and Multani family archives.
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 Saraiki, 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 Saraiki script.
Your accent comes with it: a clone sounds like you speaking Saraiki, 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 Saraiki 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": "اساں Sonex توں ڳالھ کریندے پئے ہاں، تہاݙا order سبھاݨ ݙینہہ دے 2 توں 4 وجے دے وچ delivery تھیسی۔ گھر نہ ہوو تاں SMS آلے link تے ٻیا ویلا چُݨ گھنو۔", "output_format": "mp3"}' \5 --output saraiki.mp3FAQ
Yes. The playground on this page reads up to 220 characters of Saraiki 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".
Alok, a Hindi voice, reads these samples; any voice can speak Saraiki, and you can clone a native speaker's voice from 10 seconds.
Multani is an older name for Saraiki, still used by Saraiki-speaking families in India.
$0.03125 per 1,000 characters, the same as every language.
Yes. Urdu and English words inside a Saraiki sentence are read in the same voice.
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 Saraiki script and your clone reads it in your own voice, with Saraiki pronunciation. Your natural accent carries over, so it sounds like you speaking Saraiki.
More languages
See text to speech in every language, the full list of 250+ languages, pricing, the Pāṇini TTS API, or transcribe Saraiki 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.