Text to speech · الدارجة التونسية
Pāṇini TTS reads Tunisian Derja in Arabic script, including the French words Tunisians use every day; the samples on this page are read by Nour, an Arabic voice.
الـ rendez-vous متاعك مع الطبيب نهار الإثنين على العشرة متاع الصباح، والـ consultation بخمسين دينار. باش يجيك SMS نهار قبل، وكان تحب تبدّل الوقت كلّمنا.
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 Tunisian Arabic platform voice yet, so the playground uses Nour, a voice recorded in another language: the Tunisian Arabic text is read correctly, in that voice's accent. For a local accent, clone a native Tunisian Arabic speaker from a 10-second recording and use that voice for every clip.
Sign up free, then send Tunisian Arabic 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 Tunisian Arabic
Tunisian Arabic, or Derja (تونسي), is instantly recognisable by its words: "عسلامة" (hello), "برشا" (a lot), "توّا" (now), "باهي" (good, OK), "شنوّة" (what) and "يعيشك" (thank you, literally "may God keep you alive"). Possession uses "متاع": "الموعد متاعك" (your appointment). Verbs mark "I" with n- and "we" with n- plus -u, as in "نمشيو" (we go). Tunis, Sfax and the south each have their own accent, and Italian, Turkish and Amazigh have all left words behind.
French is part of daily Tunisian speech, so customer messages read like "الرانديفو متاعك غدوة" (your appointment, rendez-vous, is tomorrow) or mix in "la facture" and "merci". Pāṇini reads Arabic with French in one voice. Tunisians understand MSA perfectly well, but on a service call they expect Derja; a clinic or bank that says "عسلامة" and "يعيشك" sounds Tunisian rather than official.
Use cases
Recharge, internet and bill calls for Tunisian mobile and broadband customers in Derja with French product names.
Clinics in Tunis and Sousse confirm appointments for local patients, and for the many visitors who travel to Tunisia for treatment.
Card and payment reminders for banks, and booking confirmations for hotels and tour operators.
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 Tunisian Arabic, 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 Tunisian Arabic script.
Your accent comes with it: a clone sounds like you speaking Tunisian Arabic, 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 Tunisian Arabic 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": "الـ rendez-vous متاعك مع الطبيب نهار الإثنين على العشرة متاع الصباح، والـ consultation بخمسين دينار. باش يجيك SMS نهار قبل، وكان تحب تبدّل الوقت كلّمنا.", "output_format": "mp3"}' \5 --output tunisian-arabic.mp3FAQ
Yes. The playground on this page reads up to 220 characters of Tunisian Arabic 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".
Nour, an Arabic voice, reads these samples; any voice can speak Tunisian Arabic, and you can clone a native speaker's voice from 10 seconds.
Yes. French words such as rendez-vous or facture are read in the same voice as the Arabic around them.
Send Arabic script for reliable results; convert text such as "3aslema, barcha" to Arabic script first.
$0.03125 per 1,000 characters, the same as every language and dialect, with 10,000 free characters and one free voice clone.
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 Tunisian Arabic script and your clone reads it in your own voice, with Tunisian Arabic pronunciation. Your natural accent carries over, so it sounds like you speaking Tunisian Arabic.
More languages
See text to speech in every language, the full list of 250+ languages, pricing, the Pāṇini TTS API, or transcribe Tunisian Arabic 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.