CosyVoice
Multilingual large voice generation model with full-stack inference, training, and deployment.
About
CosyVoice is a large multilingual text-to-speech model from FunAudioLLM. The 3.0 version supports 9 languages and 18+ Chinese dialects, focusing on content consistency, speaker similarity, and prosody naturalness. It provides pronunciation control, text normalization, streaming inference, and instructions for emotion and speech rate, with a web UI, Docker, and Python API.
Reviews (0)
Leave a Review
No reviews yet. Be the first to review!
Details
- Category
- Text-to-Speech (TTS)
- Price
- Free
- Platform
- Local/Desktop
- Difficulty
- Intermediate (3/5)
- License
- Apache-2.0
- Added
- May 7, 2026
Related Tools
Lightweight and expressive TTS model with 82M parameters for fast local inference.
Open-source dialogue TTS model by Nari Labs supporting multi-speaker conversations.
Pure language modeling approach to TTS without traditional audio codecs.
Transformer-based text-to-audio model by Suno that generates speech, music, and sound effects.
Multilingual TTS with zero-shot voice cloning and streaming support.
Emotion-controllable TTS engine by NetEase with 2000+ voices.