Arabic text-to-speech
Arabic is served by two engines: Chatterbox Multilingual, and TADA's multilingual build. It is the largest language in the set with only two options, and the choice is a real one rather than a fallback.
Two things to plan around. TADA is variant-split — only its larger multilingual model speaks Arabic, and its smaller, faster English-only build does not, so an Arabic job has to be on the right one. And the Arabic abjad costs roughly two and a half times what Latin script does in these tokenisers, so long Arabic scripts are chunked on estimated tokens rather than on characters; without that, a script well under a character limit loses its tail silently. Neither Qwen3-TTS nor Kokoro speaks Arabic, so cloning an Arabic voice means Chatterbox.
The engines that speak Arabic
- Chatterbox Multilingual
- TADA
Every engine on that list is on the same plan — there is no per-engine surcharge and no tier that unlocks one. You choose per generation.
One caveat on TADA: it ships in two sizes and only the larger, multilingual build speaks Arabic. Its smaller and faster model is English-only, so a Arabic job has to be on the right one.
Voices you can start from
PRESET VOICES
Kokoro does not speak Arabic, so its preset catalogue is not available here. Qwen3-TTS CustomVoice ships no natively Arabic preset speaker, so a preset used here is a voice speaking outside its own language.
YOUR OWN VOICE
Chatterbox Multilingual clones from a short reference clip in all 23 languages, Arabicincluded — which is the answer whenever no preset is close enough. Cloning requires that the voice is your own or that you have the speaker’s explicit permission, on every plan.
Long Arabic scripts
Arabic is written in the Arabic abjad, which costs more tokens per character than Latin script does. That matters because engines have a token ceiling they do not expose, and a splitter that counts characters overshoots it — the generation stops mid-sentence, the rest is discarded, and the request still reports success. Our splitter prices each chunk in estimated tokens with a per-script cost, so a long Arabic script is split more finely than its character count alone would suggest, and it completes.
One plan, every engine and every language: $8 a month for 2 hours of generated audio, with a 7-day free trial.
Engine coverage on this page is pinned to the studio’s own language map by a cross-package test, so it cannot drift from what you are actually offered. See the engines page for what maintaining them involves, and audio rights for what you may do with the result.