VOICE · STREAMING · CONTROL
CosyVoice
@QWENAUDIO
Let your partner speak naturally in a multilingual, cross-language, and emotion-controllable voice.
CosyVoice provides a complete speech generation stack from model to streaming service, suitable for building low-latency, multi-lingual vocal organs for partners.
Project address (can be copied to AI):https://github.com/QwenAudio/CosyVoice
PROJECT INTRO
Project introduction
CosyVoice supports multi-language and cross-language speech generation, zero-sample timbre reproduction, command-based voice control and streaming output, and provides training, inference and deployment tools.
Companion Systems It can be deployed as a local or server TTS backend for continuous sound output such as calls, voice messages, and read-alouds.
- Suitable for:A companion project that requires a multilingual, low-latency, and trainable TTS backend.
- Platform:Python with GPU self-hosted environment.
- Usage:Download the pre-trained model and run the WebUI, inference script or service interface.
- License:Apache-2.0。
COMMENTS & FEEDBACK
Comments and Feedback
People who have used this project can come back and tell newcomers: which platform it ran on, whether there were any pitfalls during the installation, and what the actual experience was like. The current version is in guest mode, and you do not need to register an account to leave a message.
The message is waiting for review and will be publicly displayed here after approval.
SOURCE & CREDIT
Atlas is responsible for the introduction and navigation, and the use still returns to the original author.
We do not mirror project files, nor do we intercept author traffic. For installation, download, version updates and the latest instructions, please refer to the project page provided by the original author.
Reading public comments...