Open-source file format designed for high-quality, customizable singing voice synthesis.
Aces is a file format specifically designed for vocal synthesis that is simple, open, user-friendly, and powerful. It has been widely used in our vocal synthesis API to meet the vast majority of user requirements. It offers high extensibility and is also highly readable.
- Easy-to-read, human-editable JSON-based format
- Multi-language support
- Introduce piece parameters that allow for the use of curves to represent pitch and energy across the entire piece
For specifics regarding the file format please refer to File Description. Examples illustrating various use-cases can be found in the ./examples/ directory.
Contributions and suggestions for modification are welcome. You can open an issue or send an email to sean.z@timedomain.ai.
We offer an API service for singing voice synthesis, please refer to the api_doc. If you're interested in testing or collaborating with us, please send an email to sean.z@timedomain.ai
This project is licensed under the MIT License - see the LICENSE file for details.