This roadmap is for EmotiVoice (易魔声), a project driven by the community. We value your feedback and suggestions on our future direction.
Please visit https://github.com/netease-youdao/EmotiVoice/issues on GitHub to submit your proposals. If you are interested, feel free to volunteer for any tasks, even if they are not listed.
The plan is to finish 0.2 to 0.4 in Q4 2023.
- Updated model with potentially improved quality.
- If time allows, release training code to support fine-tuning using your own data.
- First version of desktop application.
- Support longer text.
- Documentation: wiki page for hardware requirements. #30
- Support mixed Chinese and English input text. #28
- Resolve bugs related to certain modal particles, to make it more robust. #18
- Documentation: voice list wiki page
- Documentation: this roadmap.
- We offer a pretrained model with over 2000 voices, supporting both Chinese and English languages.
- You can perform inference using the command line interface. We also offer a user-friendly web demo for easy usage.
- For convenient deployment, we offer a Docker image.