CosyVoice3

CosyVoice3 TTS

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

Anmelden Limit fir 5. 000 Zeichen

Wrap your text in SSML tags for precise control:

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

Tags déi d'gewielt Modell verstinn - klickt fir eng an Ärem Text ze setzen wou se geschitt:

Dëse Modell liest einfache Text, sou datt Inline-Tags ignoréiert ginn. Fir Tag-baséiert Emotiounen, wielt e expressiven Modell wéi Orpheus oder Bark.

Eegen Aussproochen definéieren (Wuert = Aussprooch):

-12 +12
0.5x 2.0x
Free mat Piper, VITS, MeloTTS
Äert generéiert Audio wäert hei erscheinen. Wielt e Modell, gitt Text an a klickt op Generéieren.
Audio gouf erfollegräich generéiert
0:00
Audio erofgelueden Lëscht vu lëtzebuergesche Schrëftsteller Link expires in 24h
Den Haaptuert ass Personnes. Kommerziell Lizenz vun $5/mo
Maacht dat Är eege Stëmm Klonen eng Stëmm an 30 Sekonnen
Liewe TTS.ai? Erzielt Är Frënn!

Iwwer 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.

Bescht fir: Multilingual production TTS, real-time applications, voice cloning

All sichen CosyVoice3 Stimmen

Op ee Bléck

Entwéckler
Alibaba (FunAudioLLM)
Lizenz
Apache 2.0
Tier
standard
Geschwindegkeet
fast
Sprooche-Klonen
Ja
Sproochen
English, Chinese, Japanese, Korean, German, Spanish, French, Italian, Russian
Maximal Zeichen
5000

CosyVoice3 Stimmen

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 Lëscht vun de 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 Stimmen