Chinese text-to-speech
Chinese is served by five engines — both Qwen3-TTS variants, Chatterbox Multilingual, TADA's multilingual build and Kokoro — and it is the language Qwen3-TTS was most obviously built for. Of CustomVoice's nine preset speakers, five are natively Chinese, which is more than any other language gets.
Chinese characters cost roughly two and a half times what a Latin character costs in these models' tokenisers, so a script that looks short can be long. Our text splitter prices each chunk in estimated tokens rather than characters for exactly this reason — without it, a Chinese script comfortably under a character limit runs past the engine's hidden token ceiling and the tail is discarded silently, with the response still reporting success. Kokoro's four Chinese preset voices are all female; if you need a male Chinese voice from a preset, use Qwen3-TTS CustomVoice instead.
The engines that speak Chinese
- Qwen3-TTS
- Qwen3-TTS CustomVoice
- Chatterbox Multilingual
- TADA
- Kokoro
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 Chinese. Its smaller and faster model is English-only, so a Chinese job has to be on the right one.
Voices you can start from
PRESET VOICES
Kokoro contributes 4 preset Chinese voices. Qwen3-TTS CustomVoice adds 5 natively Chinese preset speakers.
YOUR OWN VOICE
Chatterbox Multilingual clones from a short reference clip in all 23 languages, Chinese included — 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 Chinese scripts
Chinese is written in Chinese characters, 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 Chinese script is split more finely than its character count alone would suggest, and it completes.
One plan, every engine and every language: US$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.