CosyVoice3

CosyVoice3 TTS

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

Inscrever-se para o limite de 5000 caracteres

Envolva o seu texto em tags SSML para controle preciso:

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

Etiquetas o modelo selecionado entende — clique para soltar um para o seu texto onde acontece:

Este modelo lê texto simples, por isso as etiquetas inline são ignoradas. Para emoção baseada em tags, mude para um modelo expressivo como Orpheus ou Bark.

Definir pronúncias personalizadas (palavra = pronúncia):

-12 +12
0.5x 2.0x
Grátis com Piper, VITS, MeloTTS
Seu áudio gerado aparecerá aqui. Escolha um modelo, introduza texto e clique em Gerar.
O áudio gerado com sucesso
0:00
Baixe áudio Baixar.srt A ligação expira em 24h
Gratuito nível: uso pessoal. Licença comercial a partir de $5/mo
Gosta do TTS.ai? Conte aos seus amigos!

Sobre 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.

Melhor para: Multilingual production TTS, real-time applications, voice cloning

Procurar todos CosyVoice3 vozes

De uma olhada

Desenvolvedor
Alibaba (FunAudioLLM)
Licença
Apache 2.0
Tier
standard
Velocidade
fast
Clonagem de voz
Sim
Línguas
English, Chinese, Japanese, Korean, German, Spanish, French, Italian, Russian
Número máximo de caracteres
5000

CosyVoice3 vozes

Chinese Female

Chinese
Norma Female

Chinese Male

Chinese
Norma Male

English Female

English
Norma Female

English Male

English
Norma Male

French Female

French
Norma Female

German Female

German
Norma Female

Italian Female

Italian
Norma Female

Japanese Female

Japanese
Norma Female

Korean Female

Korean
Norma Female

Russian Female

Russian
Norma Female

Spanish Female

Spanish
Norma 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.
← Todas as vozes