Audiolla

audiolla

Thirty-five audio engines. One port. Zero cloud. Fire-and-forget async jobs. Webhooks.

You needed Demucs for stems. Then librosa for BPM and key. Then basic-pitch for MIDI transcription. Then pyannote for speaker diarization. Then DeepFilterNet for speech enhancement. Then you spent three days debugging Python version conflicts and now you hate everything.

audiolla is what happens when you stop doing that.

Every audio processing tool worth using, wrapped in one HTTP API, running in one Docker container. Stage a file, POST a JSON body, get audio, JSON or MIDI back. Drive it from curl, shell scripts, Python notebooks, Makefiles, or point an LLM agent at the MCP endpoint and let it rip.

No account. No subscription. No per-minute billing. No vendor lock-in. docker run and you're done.

Contents

• What's in the box
• Run it
• Quick start
• Documentation
• Agents and MCP
• Build and dev
• Sponsor
• License

What's in the box

Run it

# no GPU

docker run --rm -it \ -v $HOME/.audiolla-data:/data \ -p 127.0.0.1:8000:8000 \ psyb0t/audiolla:latest

GPU

docker run --rm -it --gpus all \ -v $HOME/.audiolla-data:/data \ -p 127.0.0.1:8000:8000 \ psyb0t/audiolla:latest-cuda

Demucs weights download at container startup for the enabled Demucs engines and cache in /data/torch_cache/. Other models download on first use into /data. Same -v mount next time and they're already there. The CPU image carries 27 engines; the CUDA image adds the bigger Demucs variants and the generators for 35.

Going beyond localhost? Set AUDIOLLA_AUTH_TOKEN first and read the security page.

Quick start

Stage the input once, then reference it by path. Every audio endpoint takes a JSON body.

# stage your input file

curl -X PUT --data-binary @song.wav \ -H 'Content-Type: application/octet-stream' \ http://localhost:8000/v1/files/uploads/song.wav

rip the vocals out of a track

curl -X POST http://localhost:8000/v1/audio/separate \ -H 'Content-Type: application/json' \ -d '{"file_path":"uploads/song.wav","engine":"htdemucs","stems":["vocals"],"output_path":"out/vocals.wav"}' curl -o vocals.wav http://localhost:8000/v1/files/out/vocals.wav

what key is it in? what are the chords?

curl -X POST http://localhost:8000/v1/audio/chords \ -H 'Content-Type: application/json' \ -d '{"file_path":"uploads/song.wav"}'

transcribe that vocal melody to MIDI, then render it back through a SoundFont

curl -X POST http://localhost:8000/v1/audio/to_midi/basic-pitch \ -H 'Content-Type: application/json' \ -d '{"file_path":"out/vocals.wav","output_path":"out/melody.mid"}' curl -X POST http://localhost:8000/v1/midi/render \ -H 'Content-Type: application/json' \ -d '{"file_path":"out/melody.mid","output_path":"out/rendered.wav"}'

Audio in. MIDI out. Chords detected. Re-synthesized. No Python environment to set up. No API keys. Just HTTP.

Documentation

The full documentation lives at [psyb0t.github.io/docker-audiolla](https://psyb0t.github.io/docker-audiolla/).

Feature guides with curl examples: separation and restoration, mastering and effects, analysis, speech, editing, generation, MIDI, presets and pipelines, async jobs.

Agents and MCP

Point any MCP client that speaks Streamable HTTP at http://localhost:8000/v1/mcp (with Authorization: Bearer if auth is on) and it gets the audio toolset as callable tools. For Claude Code, Codex and OpenClaw there is a ready skill and plugin:

claude plugin marketplace add psyb0t/agents

claude plugin install audiolla@psyb0t

The agent integrations page covers Codex, OpenClaw and the stdio bridge. The skill also works in any agent that reads .agents/skills/, such as peen.

Build and dev

make build        # CPU image

make build-cuda # CUDA image make lint # flake8 + mypy in the dev container make test # offline unit tests in the dev container make generate # regenerate src/audiolla/schema/ from openapi.yaml make docs # build the docs site into .testing/docs-site make help # everything else

The host needs docker, make and git. Development has the details, and CHANGELOG.md has the release history.

Sponsor

License

WTFPL.

matchering and pedalboard are GPL v3. Fine for self-hosted use. Distributing the image as a product needs a GPL compliance review. THIRD_PARTY.md lists the bundled third-party components. Model weights download at runtime under their own licenses, and MusicGen's are non-commercial; the engines page has the per-model terms.