psyb0t/audiolla repository overview

# 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

- curl -X POST http://localhost:8000/v1/audio/normalize \
-     -F "[email protected]" -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

# 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"}'
# → {"path":"out/vocals.wav","size":...,"output_format":"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"}'
# → {"key":"F# minor","key_confidence":0.91,"chords":[{"chord":"F#m","start_sec":0.0,...},...]}

# transcribe that vocal melody to MIDI
curl -X PUT --data-binary @out/vocals.wav -H 'Content-Type: application/octet-stream' \
  http://localhost:8000/v1/files/uploads/vocals.wav  # only if not already staged
curl -X POST http://localhost:8000/v1/audio/to_midi/basic-pitch \
  -H 'Content-Type: application/json' \
  -d '{"file_path":"uploads/vocals.wav","output_path":"out/melody.mid"}'

# render the MIDI back to audio through a SoundFont
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"}'

# strip background noise from a voice recording
curl -X POST http://localhost:8000/v1/audio/noise-reduce/uvr-denoise \
  -H 'Content-Type: application/json' \
  -d '{"file_path":"uploads/interview.wav","output_path":"out/clean.wav"}'

# who's speaking and when?
curl -X POST http://localhost:8000/v1/audio/diarize/pyannote \
  -H 'Content-Type: application/json' \
  -d '{"file_path":"uploads/interview.wav"}'
# → {"num_speakers":2,"segments":[{"speaker":"SPEAKER_00","start_sec":0.5,"end_sec":8.2},...]}

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

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

# all 4 stems as a ZIP
curl -X POST http://localhost:8000/v1/audio/separate \
  -H 'Content-Type: application/json' \
  -d '{"file_path":"uploads/track.wav","engine":"htdemucs","output_path":"out/stems.zip"}'
curl -o stems.zip http://localhost:8000/v1/files/out/stems.zip

# stage track + reference
curl -X PUT --data-binary @track.wav -H 'Content-Type: application/octet-stream' \
  http://localhost:8000/v1/files/uploads/track.wav
curl -X PUT --data-binary @ref.wav -H 'Content-Type: application/octet-stream' \
  http://localhost:8000/v1/files/uploads/ref.wav

# match EQ + loudness to a reference track
curl -X POST http://localhost:8000/v1/audio/master \
  -H 'Content-Type: application/json' \
  -d '{"file_path":"uploads/track.wav","mode":"reference","reference_path":"uploads/ref.wav","output_path":"out/mastered.wav"}'
curl -o mastered.wav http://localhost:8000/v1/files/out/mastered.wav

# run a built-in pedalboard chain (presets: transparent, loud)
curl -X POST http://localhost:8000/v1/audio/master \
  -H 'Content-Type: application/json' \
  -d '{"file_path":"uploads/track.wav","mode":"chain","preset":"loud","output_path":"out/mastered.wav"}'
curl -o mastered.wav http://localhost:8000/v1/files/out/mastered.wav

# returns JSON. features: bpm, key, loudness, duration,
# spectral_centroid, rms, zcr. Omit features to get them all.
curl -X POST http://localhost:8000/v1/audio/analyze \
  -H 'Content-Type: application/json' \
  -d '{"file_path":"uploads/track.wav","features":["bpm","key","loudness"]}'

# beat grid — returns bpm + beat timestamps
curl -X POST http://localhost:8000/v1/audio/beats \
  -H 'Content-Type: application/json' \
  -d '{"file_path":"uploads/track.wav"}'

# onset timestamps — note attacks, transients
curl -X POST http://localhost:8000/v1/audio/onsets \
  -H 'Content-Type: application/json' \
  -d '{"file_path":"uploads/track.wav"}'

# dominant melody contour — pitch in Hz per frame
curl -X POST http://localhost:8000/v1/audio/melody \
  -H 'Content-Type: application/json' \
  -d '{"file_path":"uploads/track.wav"}'

# structural segmentation — labels recurring sections A, B, C...
curl -X POST http://localhost:8000/v1/audio/segments \
  -H 'Content-Type: application/json' \
  -d '{"file_path":"uploads/track.wav","num_segments":6}'

# find silent gaps in a recording (no trim_mode → JSON only)
curl -X POST http://localhost:8000/v1/audio/silence \
  -H 'Content-Type: application/json' \
  -d '{"file_path":"uploads/track.wav","threshold_db":-30,"min_duration_sec":1.0}'

# trim all silence and stage the result
curl -X POST http://localhost:8000/v1/audio/silence \
  -H 'Content-Type: application/json' \
  -d '{"file_path":"uploads/track.wav","threshold_db":-30,"min_duration_sec":0.5,"trim_mode":"all","output_path":"out/trimmed.wav"}'
curl -o trimmed.wav http://localhost:8000/v1/files/out/trimmed.wav

# trim only leading/trailing silence
curl -X POST http://localhost:8000/v1/audio/silence \
  -H 'Content-Type: application/json' \
  -d '{"file_path":"uploads/track.wav","threshold_db":-40,"min_duration_sec":0.3,"trim_mode":"edges","output_path":"processed/trimmed.wav"}'

# Static PNG spectrogram (color + scale params)
curl -X POST http://localhost:8000/v1/audio/visualize/image/spectrogram \
  -H 'Content-Type: application/json' \
  -d '{"file_path":"uploads/track.wav","width":1280,"height":720,"output_path":"out/spec.png"}'
curl -o spec.png http://localhost:8000/v1/files/out/spec.png

# Static PNG waveform (color param)
curl -X POST http://localhost:8000/v1/audio/visualize/image/waveform \
  -H 'Content-Type: application/json' \
  -d '{"file_path":"uploads/track.wav","width":1280,"height":240,"output_path":"out/wave.png"}'
curl -o wave.png http://localhost:8000/v1/files/out/wave.png

# Animated MP4 spectrum analyser (fps + container params)
curl -X POST http://localhost:8000/v1/audio/visualize/video/spectrum \
  -H 'Content-Type: application/json' \
  -d '{"file_path":"uploads/track.wav","width":1280,"height":720,"fps":30,"container":"mp4","output_path":"out/viz.mp4"}'
curl -o viz.mp4 http://localhost:8000/v1/files/out/viz.mp4

# Chromaprint fingerprint — identifies a recording regardless of encoding
curl -X POST http://localhost:8000/v1/audio/fingerprint \
  -H 'Content-Type: application/json' \
  -d '{"file_path":"uploads/track.wav"}'
# → {"duration": 215.34, "fingerprint": "AQADtEqRRIuQ..."}

# include the raw integer array (for custom similarity scoring)
curl -X POST http://localhost:8000/v1/audio/fingerprint \
  -H 'Content-Type: application/json' \
  -d '{"file_path":"uploads/track.wav","return_raw":true}'

# Remove room reverb (BS-Roformer, SDR 19+)
curl -X POST http://localhost:8000/v1/audio/restore/uvr-dereverb \
  -H 'Content-Type: application/json' \
  -d '{"file_path":"uploads/track.wav","output_path":"out/dry.wav"}'

# Remove echo — normal mode
curl -X POST http://localhost:8000/v1/audio/restore/uvr-deecho \
  -H 'Content-Type: application/json' \
  -d '{"file_path":"uploads/track.wav","output_path":"out/noecho.wav"}'

# Remove echo — aggressive mode (same engine, harder suppression)
curl -X POST http://localhost:8000/v1/audio/restore/uvr-deecho \
  -H 'Content-Type: application/json' \
  -d '{"file_path":"uploads/track.wav","aggressive":true,"output_path":"out/noecho.wav"}'

# Remove broadband background noise — ML (MelBand Roformer, SDR 28)
curl -X POST http://localhost:8000/v1/audio/restore/uvr-denoise \
  -H 'Content-Type: application/json' \
  -d '{"file_path":"uploads/track.wav","output_path":"out/clean.wav"}'

# Any audio → MIDI file (staged)
curl -X POST http://localhost:8000/v1/audio/to_midi/basic-pitch \
  -H 'Content-Type: application/json' \
  -d '{"file_path":"uploads/guitar_riff.wav","output_path":"out/riff.mid"}'
curl -o riff.mid http://localhost:8000/v1/files/out/riff.mid

# Tune the detection thresholds
curl -X POST http://localhost:8000/v1/audio/to_midi/basic-pitch \
  -H 'Content-Type: application/json' \
  -d '{"file_path":"uploads/piano.wav","onset_threshold":0.6,"frame_threshold":0.3,"minimum_note_length_ms":80,"output_path":"out/piano.mid"}'

# Write directly to a different staging path
curl -X POST http://localhost:8000/v1/audio/to_midi/basic-pitch \
  -H 'Content-Type: application/json' \
  -d '{"file_path":"recordings/bass.wav","output_path":"midi/bass_notes.mid"}'
# → {"path":"midi/bass_notes.mid","size":...,"engine":"basic-pitch","output_format":"mid"}