On the recordRead 12 Oct 202627 facts
Shao
On the record
- Audience
- The current release is mainly intended for researchers and developers familiar with GPU servers and Docker/CUDA workflows.shao-music-ai.github.io · read 12 Oct 2026
- Audio export formats
- mp3_and_wavgithub.com · read 22 Sep 2026
- Audio upload
- Nogithub.com · read 22 Sep 2026
- Commercial use
- Nogithub.com · read 22 Sep 2026
- Compute requirements
- The full inference pipeline recommends an NVIDIA GPU with at least 24GB VRAM, Docker, NVIDIA Container Toolkit, and a CUDA-compatible driver.github.com · read 12 Oct 2026
- Demo
- The project links to an online audio demo page for generated samples.shao-music-ai.github.io · read 12 Oct 2026
- Deployment
- The documented setup runs the frontend and backend in Docker with an NVIDIA GPU, and recommends at least 24 GB of VRAM for the full inference pipeline.shao-music-ai.github.io · read 12 Oct 2026
- Deployment guide
- The maker lists a full deployment guide for musicians and beginners as coming soon.shao-music-ai.github.io · read 12 Oct 2026
- Generation pipeline
- Its two-stage pipeline generates coarse acoustic tokens, completes higher RVQ token layers with super-resolution, and decodes them into a waveform.github.com · read 12 Oct 2026
- Included components
- The release includes a frontend UI, FastAPI backend dispatcher, single-GPU inference worker, and an end-to-end audio generation path.github.com · read 12 Oct 2026
- Inference limitation
- The maker says results may vary across GPU types and that incompatible containers or software versions can cause severely degraded, noise-like audio.github.com · read 12 Oct 2026
- Intended users
- The current release is mainly intended for researchers and developers familiar with GPU servers and Docker/CUDA workflows.github.com · read 12 Oct 2026
- License
- The model weights are stated to be intended for release under CC BY-NC 4.0.github.com · read 12 Oct 2026
- Model representation
- The system uses a 64-layer RVQ acoustic-token hierarchy.github.com · read 12 Oct 2026
- Model weights license
- The model weights are currently intended to be released under CC BY-NC 4.0.github.com · read 12 Oct 2026
- Product
- Shao is an open-source system for generating high-fidelity, full-length music from text descriptions and lyric conditions.github.com · read 12 Oct 2026
- Prompt controls
- Natural-language prompts and lyrics can control style, mood, vocals, and content.github.com · read 12 Oct 2026
- Purpose
- Shao is an open-source system for generating full-length music from text descriptions and lyric conditions.github.com · read 12 Oct 2026
