---
license: mit
pipeline_tag: audio-to-audio
---
[FAcodec](https://arxiv.org/pdf/2403.03100) trained on 50k hours speech data, with more timbre diversity and better at reconstructing speakers from podcasts, videos, games or animations.  
This is a separate decoder designed and trained based on the pretrained [encoder](https://huggingface.co/Plachta/FAcodec) specifically for voice conversion task.  
It is capable of zero-shot voice conversion, stream voice conversion and has outstanding timbre generalization ability.  

See [main repository](https://github.com/Plachtaa/FAcodec) for example usages.