CosyVoice3

CosyVoice3 TTS

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

Akaụntụ maka 5,000 akara oghe

Kpọchie ngwe gị n'ime SSML táàbụ̀ maka nlekọta ziri ezi:

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

Táàbụ̀ nke móòdù ahụ a họọrọ na-aghọta - pịa ka ịkpụga otu n'ime ngwe gị ebe ọ na-eme:

Móòdù a na-agụ ngwe nkịtị, yabụ na a na-ewepụta inline táàbụ̀. Maka táàbụ̀-n'okpuru n'émóòdù, gbanwee ka móòdù na-egosi ihe dịka Orpheus mọọbụ Bark.

Ndesịta okwu emeredịkachọrọ:

-12 +12
0.5x 2.0x
Free na Piper, VITS, MeloTTS
Ọdịdị gị ga-egosipụta ebe a. Họrọ móòdù, tinye ngwe, ma pịa Kewapụta.
Ọdịdị a mepụtala nke ọma
0:00
Bubata ụda Bubata.srt Ndesịta njikọ ahụ ga-agwụ n'ime 24h
Free tier: ojiji onwe onye. Commercial license site na $5/mo
Mee ka ọ bụrụ ụda gị Kloo ụda n'ime sekọnd 30
Ị hụrụ TTS.ai? Kpọtụrụ enyi gị!

_N'ihe banyere 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.

Ọkachasị maka: Multilingual production TTS, real-time applications, voice cloning

Nlegharịa niile CosyVoice3 ụda

N'ime nlele

Ńkwádò
Alibaba (FunAudioLLM)
Ikikere
Apache 2.0
Tier
standard
Nhazi
fast
Nhazi ụda
Ee
Asụsụ ndị ahụ
English, Chinese, Japanese, Korean, German, Spanish, French, Italian, Russian
Ụhara Max
5000

CosyVoice3 ụda

Chinese Female

Chinese
Dìfọ́ọ̀ltụ̀ Female

Chinese Male

Chinese
Dìfọ́ọ̀ltụ̀ Male

English Female

English
Dìfọ́ọ̀ltụ̀ Female

English Male

English
Dìfọ́ọ̀ltụ̀ Male

French Female

French
Dìfọ́ọ̀ltụ̀ Female

German Female

German
Dìfọ́ọ̀ltụ̀ Female

Italian Female

Italian
Dìfọ́ọ̀ltụ̀ Female

Japanese Female

Japanese
Dìfọ́ọ̀ltụ̀ Female

Korean Female

Korean
Dìfọ́ọ̀ltụ̀ Female

Russian Female

Russian
Dìfọ́ọ̀ltụ̀ Female

Spanish Female

Spanish
Dìfọ́ọ̀ltụ̀ Female

CosyVoice3 TTS - Ajụjụ ndị na-emekarị

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.
← Agụgụala niile