- Home
- AI Music Generators
- Khala (now Shao)
On the recordRead 12 Oct 202625 facts
Khala (now Shao)
On the record
- Audience
- The current release is mainly intended for researchers and developers familiar with GPU servers and basic Docker and CUDA workflows.github.com · read 12 Oct 2026
- Commercial use
- Nonanhuantech.com · read 22 Sep 2026
- Compatibility limitation
- Generation quality can vary with GPU architecture and software versions, and the project says bit-identical output across GPU types is not guaranteed.github.com · read 12 Oct 2026
- Deployment
- The README provides Docker setup instructions and a local web UI at 127.0.0.1:30869.github.com · read 12 Oct 2026
- Former name
- The project was formerly called Khala and has been officially renamed Shao.github.com · read 12 Oct 2026
- Full-song generation
- It is designed to generate full-length musical works rather than short clips or loop-style accompaniment.github.com · read 12 Oct 2026
- Generation architecture
- Its pipeline uses a 64-layer residual vector quantization acoustic-token hierarchy, followed by a super-resolution model and decoder.github.com · read 12 Oct 2026
- Generation controls
- Natural-language prompts and lyrics can control style, mood, vocals, and content.github.com · read 12 Oct 2026
- Generation pipeline
- Its pipeline generates coarse acoustic tokens, completes higher RVQ token layers with a super-resolution model, and decodes the waveform.github.com · read 12 Oct 2026
- GPU requirement
- The full inference pipeline recommends an NVIDIA GPU with at least 24 GB of VRAM, such as an RTX 4090 or higher-tier GPU.github.com · read 12 Oct 2026
- GPU requirements
- The full inference pipeline recommends an NVIDIA GPU with at least 24 GB of VRAM, such as an RTX 4090 or higher-tier GPU.github.com · read 12 Oct 2026
- Included system
- The project includes a frontend UI, FastAPI backend dispatcher, single-GPU inference worker, model loading, and an end-to-end audio-generation path.github.com · read 12 Oct 2026
- Intended users
- The current release is mainly intended for researchers and developers familiar with GPU servers.github.com · read 12 Oct 2026
- Model license
- The linked model weights are listed as CC BY-NC 4.0.huggingface.co · read 12 Oct 2026
- Model weights license
- The model weights are stated to be intended for release under CC BY-NC 4.0.github.com · read 12 Oct 2026
- Name change
- The project was formerly called Khala and has been officially renamed to Shao, with its model, codebase, and research direction unchanged.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, formerly Khala, is an open-source system for generating complete music from text descriptions and lyric conditions.github.com · read 12 Oct 2026
