Arabic text to speech: AI voices that read Arabic
Arabic is one of the 31 languages of Supertonic 3, the open text-to-speech model behind SuperClonica, so every voice in the catalog reads Arabic: narrators, male and female voices, characters from games, anime, cartoons and films. You can hear any of them say your own Arabic line for free, and voice long Arabic texts offline on your own computer without a character limit.
This guide explains how to get the best Arabic from it, honestly: how to write the text, what the engine does with numbers, what accent to expect and how to get the voice you need.
Try any voice in Arabic for free
On the page of any voice, choose Arabic next to the text field, type a phrase of 30 to 100 characters and press Voice it. You hear your words in that voice in a few seconds and can download the recording. No account is needed.
Write Arabic the way it should sound
Short sentences with clear punctuation sound the most natural.
- Write in Arabic script; Arabic written in Latin letters and numbers (Arabizi) may be read less accurately.
- Vowel marks (tashkeel) on ambiguous words can help the model choose the right reading.
- Numbers can stay as digits: the engine spells them as Arabic words before synthesis.
- Keep sentences short and end them with a full stop or question mark (؟).
What accent to expect
The voices in the catalog were made from English and Russian recordings. They keep their timbre in Arabic, and the accent of the original can be heard, a little for some voices and more for others. No voice in the catalog is recorded in Arabic yet: listen to the demo and your own line first, or make the first one.
Get a voice recorded in Arabic
For a native Arabic voice of your own, train one from a clean recording of 5 to 10 seconds in Arabic, your own voice or a speaker who agreed, in the studio on a computer with an NVIDIA graphics card. No graphics card? Order the voice on the exchange: an author trains it from your recording, and you pay only after you accept it.
Unlimited Arabic offline
For long texts, download the voice file and install the free SuperClonica engine: python -m pip install superclonica-cpu. Then voice a text file with one command: superclonica --text "$(cat text.ar.txt)" --voice voice.json --lang ar --output ar.wav. It runs on an ordinary processor, offline, with no character limit and no monthly fee.