Audiolla

audiolla

Thirty 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. POST a file. 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.

---

What's in the box

---

Table of Contents

• Run it
• Quick start
• What it can do
• Split stems
• Master
• Analyze
• Beats, onsets, melody, segments
• Silence detection and trimming
• Visualize (spectrogram, waveform, video)
• Acoustic fingerprint
• De-reverb, de-echo, de-noise
• Audio-to-MIDI transcription
• Neural speech and vocal enhancement
• Chord and key detection
• Voice activity detection
• Speaker diarization
• Transform
• Loudness measurement
• Loudness curve
• Loudness normalization
• HPSS (harmonic/percussive split)
• Spectral noise reduction
• Time-stretch and pitch-shift
• Pitch correct
• Repair
• Audio tagging
• Audio embeddings
• Zero-shot classification
• Audio info
• Trim
• Mix
• Concat
• Speed
• Convert
• Similar
• MIDI quantize
• Fade
• Reverse
• Loop
• BPM match
• Stereo width
• Split
• Pan
• EQ
• Key match
• Sidechain duck
• Effects chain
• Loop point
• Compose MIDI
• Inspect MIDI
• Transform MIDI
• Render MIDI to audio
• Generate music from a spec
• Drum pattern
• Chords to MIDI
• Audio metadata tags
• Clip detection
• Mid/Side encode and decode
• Beat slice
• Convolution reverb
• Transient shaper
• Multiband compression
• DJ prep
• De-ess
• Stereo field analysis
• Audio thumbnail
• MIDI humanize
• Batch operations
• Async jobs and webhooks
• Stage files
• Remote URLs
• Engines
• Workflows — presets + pipeline
• API catalog
• Endpoints
• MCP
• Agent integrations
• Configuration
• What's not in here
• Build & dev
• Supply chain
• License

---

Run it

# no GPU

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

GPU

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

Demucs weights prefetch at container startup (for whichever variants are enabled) and cache in /data/torch_cache/. First boot downloads them; same -v mount next time and they're already there. Other engines (matchering, pedalboard, librosa, sox, fx, midi) have no weights — they're ready as soon as /healthz is green.

---

Migration from v0.23.x → v1.0.0

v1.0.0 is a breaking API release. Every existing client breaks. The new shape:

• Every audio endpoint takes a JSON body (no more multipart/form-data except at /v1/files)
• Input is `file_path` (FILES_DIR-relative) xor `file_url` (server-side fetch). Pre-stage the file via PUT /v1/files/{path} first.
• Output requires `output_path` xor `output_url`. No more raw audio bytes in responses.
• Async path: async_job=true auto-stages to jobs/{id}.{ext} if neither output is given.
• MCP audio-producing tools dropped audio_base64 (and midi_base64 / image_base64 / video_base64). Same output_path xor output_url requirement.
• openapi.yaml is now the contract — Pydantic models regenerate from it via make generate. Never hand-edit src/audiolla/schema/_generated.py.

- curl -X POST http://localhost:8000/v1/audio/normalize \

• -F "file=@track.wav" -F "target_lufs=-14" -o normalized.wav

• # 1) stage the file (multipart only lives here now)
• curl -X PUT --data-binary @track.wav \
• -H 'Content-Type: application/octet-stream' \
• http://localhost:8000/v1/files/uploads/track.wav

• # 2) process via JSON body — response is JSON, not bytes
• curl -X POST http://localhost:8000/v1/audio/normalize \
• -H 'Content-Type: application/json' \
• -d '{"file_path":"uploads/track.wav","target_lufs":-14,"output_path":"out/normalized.wav"}'

• # 3) retrieve the result
• curl -o normalized.wav http://localhost:8000/v1/files/out/normalized.wav

Why? See the v1.0.0 CHANGELOG entry for the full rationale.

Quick start

Once the container is up, this is a complete audio pipeline in six commands (every audio endpoint is JSON-body now; stage your input file at /v1/files/... first):

# 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/