Text to speech · العربية الفصحى
Arabic text to speech (Arabic TTS) reads Modern Standard Arabic and the Arabic dialects people speak, including Gulf, Egyptian and Levantine, from ordinary text without tashkeel. Play it free below with no login, read by Nour, an Arabic platform voice, then use the same voice through the API. تحويل النص إلى صوت بالعربي: اكتب النص واسمعه فورًا.
نذكّركم بأن دفعة بطاقتكم الائتمانية بقيمة ألف ومئتي درهم مستحقة يوم الخميس القادم، ويمكنكم السداد مباشرة عبر الـ app أو من خلال الـ link الذي سنرسله لكم في رسالة SMS.
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
Nour, a native Arabic platform voice, reads the playground above. Any Sonex Labs voice can also read Arabic, keeping its own accent, and a voice cloned from a 10-second recording of a Arabic speaker carries that speaker's accent.
Sign up free, then send 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 Arabic (Modern Standard Arabic)
Modern Standard Arabic (الفصحى) is the shared written language of the Arab world: news bulletins, government notices, contracts, school books and many IVR menus use it, while people speak a local dialect at home. Businesses in the Gulf usually choose MSA for anything formal or legal: account statements, regulatory disclosures, emergency and public announcements, and the opening "للعربية اضغط واحد" (for Arabic, press one) of a phone menu. A single MSA recording is also understood from Casablanca to Muscat, which makes it the safe default when callers come from many countries.
Written MSA usually leaves out the short vowels, the tashkeel (تشكيل). The word علم can be عِلْم (knowledge), عَلَم (flag) or عَلِمَ (he knew), and the reader picks the right one from context. Pāṇini reads ordinary undiacritised text, and you can add diacritics where a name or rare word must be read one particular way. MSA also keeps case endings and the full sounds of ق (q), ث (th) and ذ (dh) that many dialects change, so it sounds formal on a call; for friendly conversation most companies switch to the caller's dialect.
Arabic dialects
Write in the dialect's own spelling and Pāṇini reads those words. The platform's Arabic voices are Modern Standard Arabic voices, so for a local accent, clone a native speaker of the dialect from a 10-second sample. Each dialect has its own page and playground.
Use cases
Banks, telecoms and government services in the Gulf record menus, statement alerts and regulatory messages in MSA that every Arabic speaker understands.
Narration of articles, lessons and books, where standard Arabic is expected and diacritics can fix the reading of names.
Companies serving callers across the Arab world use MSA where a single dialect would favour one country.
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 Arabic (Modern Standard 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 Arabic (Modern Standard Arabic) script.
Your accent comes with it: a clone sounds like you speaking Arabic (Modern Standard 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 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": "نذكّركم بأن دفعة بطاقتكم الائتمانية بقيمة ألف ومئتي درهم مستحقة يوم الخميس القادم، ويمكنكم السداد مباشرة عبر الـ app أو من خلال الـ link الذي سنرسله لكم في رسالة SMS.", "output_format": "mp3"}' \5 --output arabic.mp3FAQ
Modern Standard Arabic and the Arabic dialects your customers use, including Gulf (Khaleeji), Egyptian, Levantine, Najdi, Iraqi, Moroccan, Algerian, Tunisian and Sudanese. Write the text in the dialect's own spelling. The platform's Arabic voices, Nour and Tariq, are Modern Standard Arabic voices; for a local accent, clone a native speaker of the dialect from 10 seconds.
Yes. The playground on this page reads up to 220 characters of 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".
Yes. Nour, an Arabic voice, reads these samples; any Sonex Labs voice can speak Arabic, and you can clone a native speaker's voice from 10 seconds.
No. Pāṇini reads ordinary undiacritised Arabic. Add diacritics only where a word could be read more than one way and you need a specific reading.
Use MSA for formal notices, IVR menus and audiences from many countries; use the caller's dialect for friendly conversation. Pāṇini reads both, and Arabic mixed with English or French, in one voice.
$0.03125 per 1,000 characters, the same as every language and dialect. The first 10,000 characters and one voice clone are free, with no card.
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 Arabic script and your clone reads it in your own voice, with Arabic pronunciation. Your natural accent carries over, so it sounds like you speaking Arabic.
Related tools
More languages
See text to speech in every language, the full list of 250+ languages, pricing, the Pāṇini TTS API, or transcribe Arabic (Modern Standard Arabic) audio with Arabic (Modern Standard Arabic) 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.