CosyVoice3 TTS
Alibaba FunAudioLLM's latest multilingual model with ~150ms bi-streaming, instruction control, and zero-shot cloning.
Bungkus teks Anda dalam tag SSML untuk kendali yang tepat:
<speak><prosody rate="slow">Slow speech</prosody></speak>
Tag yang dipilih mengerti klik °C untuk memasukkan satu ke dalam teks Anda di mana hal itu terjadi:
Model ini membaca teks biasa, sehingga tag inline diabaikan. Untuk tag berbasis emosi, beralih ke model ekspresif seperti Orpheus atau Bark.
Definisikan pengucapan ubahan (kata = pelafalan):
Tentang 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.
Terbaik untuk: Multilingual production TTS, real-time applications, voice cloning
Jelajahi semua CosyVoice3 suaraPada sekilas
- Pengembang
- Alibaba (FunAudioLLM)
- Lisensi
- Apache 2.0
- Tier
- standard
- Kecepatan
- fast
- Penklonan Suara
- Ya
- Bahasa
- English, Chinese, Japanese, Korean, German, Spanish, French, Italian, Russian
- Karakter maksimal
- 5000