# AudioGPT

**AudioGPT** connects ChatGPT and a series of Audio Foundation Models to enable **sending** and **receiving** speech, sing, and audio during chatting.


## Capability
Here we list the capability of AudioGPT at this time. More supported models and tasks are comming soon.

|           Task            |         Foundation Model         | Status |
|:-------------------------:|:--------------------------------:|:------:|
| ----------Speech--------- |                /                 |   /    |
|      Text-to-Speech       | [FastSpeech](), [SyntaSpeech]()  |  WIP   |
|      Neural Vocoding      |    [BigVGAN](), [FastDiff]()     |  WIP   |
|      Style Transfer       |         [GenerSpeech]()          |  WIP   |
|    Speech Recognition     |           [whisper]()            |  Yes   |
|  ----------Sing---------  |                /                 |        |
|       Text-to-Sing        |          [DiffSinger]()          |  Yes   |
| ----------Audio---------  |                /                 |        |
|       Text-to-Audio       |        [Make-An-Audio]()         |  Yes   |
|     Audio Inpainting      |        [Make-An-Audio]()         |  WIP   |
|      Image-to-Audio       |        [Make-An-Audio]()         |  Yes   |



## Internal Version Updates

3.23 Support Text-to-Sing\
3.21 Support Image-to-Sing\
3.19 Support Speech Recognition\
3.17 Support Text-to-Audio

## Acknowledgement
We appreciate the open source of the following projects:

[Visual ChatGPT](https://github.com/microsoft/visual-chatgpt)  
[Hugging Face](https://github.com/huggingface)  
[LangChain](https://github.com/hwchase17/langchain)  
[Stable Diffusion](https://github.com/CompVis/stable-diffusion)