# CosyVoice-ComfyUI **Repository Path**: toppower_admin/CosyVoice-ComfyUI ## Basic Information - **Project Name**: CosyVoice-ComfyUI - **Description**: No description available - **Primary Language**: Unknown - **License**: Apache-2.0 - **Default Branch**: main - **Homepage**: None - **GVP Project**: No ## Statistics - **Stars**: 0 - **Forks**: 0 - **Created**: 2024-09-11 - **Last Updated**: 2024-09-11 ## Categories & Tags **Categories**: Uncategorized **Tags**: None ## README # CosyVoice-ComfyUI a comfyui custom node for [CosyVoice](https://github.com/FunAudioLLM/CosyVoice),you can find workflow in [workflows](./workflows/) ## new Feature suport `srt` file to single voice or mutiple voice clone input - [tts_srt](./workflows/dubbing/zh_test.srt) - [prompt_wav](./workflows/dubbing/test.mp3) - [prompt_srt](./workflows/dubbing/en_test.srt)(optional) output ## Example test on 2080ti 11GB torch==2.3.0+cu121 python 3.10.8 use case | tts_text | prompt_text | prompt_wav | instruct_text | output ----- | ---- | ---- | ---- | ---- | ---- `base tts` | `你好,我是通义生成式语音大模型,请问有什么可以帮您的吗` | | | |