CosyVoice3

CosyVoice3 TTS

Alibaba FunAudioLLM's latest multilingual model with ~150ms bi-streaming, instruction control, and zero-shot cloning.

Sign up for 5,000 character limit

Wrap your text in SSML tags for precise control:

<speak><prosody rate="slow">Slow speech</prosody></speak>

Tags the selected model understands — click to drop one into your text where it happens:

This model reads plain text, so inline tags are ignored. For tag-based emotion, switch to an expressive model like Orpheus or Bark.

Define custom pronunciations (word = pronunciation):

-12 +12
0.5x 2.0x
Free with Piper, VITS, MeloTTS
Your generated audio will appear here. Choose a model, enter text, and click Generate.
Audio Generated Successfully
0:00
Download Audio Download .srt Link expires in 24h
Free tier: personal use. Commercial license from $5/mo
Love TTS.ai? Tell your friends!

About CosyVoice3

CosyVoice3 is the newest generation from Alibaba's FunAudioLLM team and a clear step up from CosyVoice 2. It introduces bi-streaming inference with roughly 150ms latency and instruction-based control, letting you steer emotion, speed, and volume through prompts. Speaker similarity for zero-shot voice cloning is improved, and coverage spans 9 languages plus 18 Chinese dialects. An RL-tuned variant pushes prosody to a state-of-the-art level. With a 5,000-character ceiling, fast generation, and strong cloning, it's geared toward multilingual production TTS and real-time applications.

Best for: Multilingual production TTS, real-time applications, voice cloning

Browse all CosyVoice3 voices

At a glance

Developer
Alibaba (FunAudioLLM)
License
Apache 2.0
Tier
standard
Speed
fast
Voice cloning
Yes
Languages
English, Chinese, Japanese, Korean, German, Spanish, French, Italian, Russian
Max characters
5000

CosyVoice3 voices

Chinese Female

Chinese
Standard Female

Chinese Male

Chinese
Standard Male

English Female

English
Standard Female

English Male

English
Standard Male

French Female

French
Standard Female

German Female

German
Standard Female

Italian Female

Italian
Standard Female

Japanese Female

Japanese
Standard Female

Korean Female

Korean
Standard Female

Russian Female

Russian
Standard Female

Spanish Female

Spanish
Standard Female

CosyVoice3 TTS — FAQ

CosyVoice3 adds bi-streaming inference at around 150ms latency, instruction-based control over emotion/speed/volume, improved speaker similarity for cloning, and coverage of 9 languages plus 18 Chinese dialects, with an RL-tuned variant for state-of-the-art prosody.

Yes. It supports zero-shot voice cloning from a reference clip (around 3 seconds minimum) with improved speaker similarity over the previous generation.

Yes. CosyVoice3 is licensed under Apache 2.0, permitting commercial use.
← All voices