Text to speech · فارسی
Pāṇini TTS reads Persian in its own script and in the spoken register people use on the phone, not the formal Persian of the news.
قسط کارت اعتباریتون، یعنی دو میلیون و پونصد هزار تومن، تا پنجشنبه سررسید می‌شه. می‌تونید از app پرداخت کنید، یا همین الان link رو براتون SMS کنم.
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 Persian platform voice yet, so the playground uses Nour, a voice recorded in another language: the Persian text is read correctly, in that voice's accent. For a local accent, clone a native Persian speaker from a 10-second recording and use that voice for every clip.
Sign up free, then send Persian 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 Persian (Farsi)
Persian is written right to left in a Perso-Arabic alphabet of 32 letters, four more than Arabic: پ, چ, ژ and گ. Short vowels are not written, and neither is the ezafe, the short -e that links words in phrases like کارت بانکی (kart-e banki, bank card), so a voice has to supply it from knowing the language. The half-space matters as well: می‌خواهم keeps its prefix apart without breaking the word, and text typed with a full space or none at all can be read differently.
Written and spoken Persian are far apart. می‌خواهم (I want) is said می‌خوام, and است usually shrinks to a short -e, so a call that reads formal written Persian sounds like a news bulletin. The samples here are written the way people talk. Persian has borrowed widely: Arabic gave وقت (time) and لطفاً (please), French gave مرسی (thanks), and English adds words like اپلیکیشن. For banks, airlines, clinics and delivery services serving Persian speakers in Iran and abroad, a reminder in natural spoken Farsi sounds like a person, not a form letter.
Use cases
Clinics, dentists and salons serving Persian-speaking customers confirm bookings in casual spoken Farsi.
Airlines, travel agents and money-transfer services reach Persian speakers in the Gulf, Europe and North America.
Persian poetry, audiobooks and explainer videos, read with one consistent cloned narrator.
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 Persian (Farsi), 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 Persian (Farsi) script.
Your accent comes with it: a clone sounds like you speaking Persian (Farsi), 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 Persian 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": "قسط کارت اعتباریتون، یعنی دو میلیون و پونصد هزار تومن، تا پنجشنبه سررسید می‌شه. می‌تونید از app پرداخت کنید، یا همین الان link رو براتون SMS کنم.", "output_format": "mp3"}' \5 --output persian.mp3FAQ
Yes. The playground on this page reads up to 220 characters of Persian 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 register you write. For calls, spoken forms such as می‌خوام instead of می‌خواهم sound most natural.
This page covers Iranian Persian. Dari text uses the same script and can be sent as written; test a sample with the vocabulary your listeners use.
Nour reads these samples; any Sonex Labs voice can speak Persian, 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 Persian script and your clone reads it in your own voice, with Persian pronunciation. Your natural accent carries over, so it sounds like you speaking Persian.
More languages
See text to speech in every language, the full list of 250+ languages, pricing, the Pāṇini TTS API, or transcribe Persian (Farsi) 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.