Amphion
Open-source toolkit for audio, music, and speech generation research.
About
Amphion by OpenMMLab is an open-source toolkit for audio, music, and speech generation built to support reproducible research and help newcomers get started. It covers text-to-speech, singing voice synthesis, voice conversion, and music generation, and includes visualizations of classic model architectures to aid understanding. Its aim is a platform for converting any input into audio. Released under the Apache 2.0 license.
Reviews (0)
Leave a Review
No reviews yet. Be the first to review!
Details
- Category
- Music & Audio Generation
- Price
- Free
- Platform
- Local/Desktop
- Difficulty
- Advanced (4/5)
- License
- Apache-2.0
- Minimum VRAM
- 8 GB
- Added
- Apr 3, 2026
Related Tools
Fast music generation model producing full songs with lyrics in seconds.
Original latent diffusion model for text-to-audio generation.
State-of-the-art music source separation model by Meta for splitting tracks.
High-fidelity neural audio codec by Meta for audio compression and tokenization.
Text-to-music generation model using cascaded latent diffusion.
Updated music generation model with improved quality and longer generation.