CosyVoice3 TTS
Alibaba FunAudioLLM's latest multilingual model with ~150ms bi-streaming, instruction control, and zero-shot cloning.
Daangeessii kitaaba keessan keessaa tag SSML akka itti fayyadamtan:
<speak><prosody rate="slow">Slow speech</prosody></speak>
Tag'oota mo'ellaa filatamee beekuu - cuqaasi akka tokkotti galchiin gara teekstaatti yoo ta'e:
Mo'ellaan kun kitaaba salphaa baraa, kan akka taggaa inniin linjii hin beekkamne. Akka taggaa-based emooshiniitti, mo'ellaa akka Orpheus ykn Bark.
Haalli fuula
Fuulaa 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.
Fakkeenyaaf: Multilingual production TTS, real-time applications, voice cloning
Fuulaa CosyVoice3 DhaamsaAkkasumas
- Deebi'aa
- Alibaba (FunAudioLLM)
- Lizenz
- Apache 2.0
- Daandiin
- standard
- Jijjiiramni
- fast
- Dhaabbilee
- Ya
- Afaan Oromoo
- English, Chinese, Japanese, Korean, German, Spanish, French, Italian, Russian
- Akkasumas
- 5000