Self-hosted audio API in one Docker container. Stem separation, mastering, MIR (BPM/key/chords), audio→MIDI, text-to-music + SFX (MusicGen/Stable Audio/Riffusion/AudioLDM2), diarization, speech enhancement, restoration, embeddings + zero-shot tagging, workflows, async + webhooks. REST + MCP. CPU + CUDA.
Latest release v2.0.2 · 9 Nov 2026
2 files for Codex, OpenCode and Claude Code: docker-audiolla AGENTS.md, docker-audiolla CLAUDE.md — 4,834 tokens loaded in every session.
AGENTS.md A 4,831 tok CLAUDE.md A 3 tok These files are psyb0t/docker-audiolla's own configuration — they tell Codex, OpenCode and Claude Code how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.