librosa
Python package for music and audio analysis: feature extraction, beat tracking, and spectrograms.
| Language | Python |
|---|---|
| Category | Audio analysis |
| License | ISC |
| Platforms | macOS Windows Linux |
| Install | pip install librosa |
| First released | 2013 |
| Maintained | Yes |
| Links | Website · Source |
Strengths
- De-facto standard for MIR feature extraction
- Extensive, well-documented API and tutorials
- Pure-Python, easy cross-platform install
Limitations
- Analysis-only: no real-time audio or synthesis
- Can be slow/memory-heavy on large batches
Best for
Music information retrieval and audio feature extraction for research and ML.
Minimal example
import librosa
y, sr = librosa.load(librosa.ex('trumpet'))
tempo, beats = librosa.beat.beat_track(y=y, sr=sr)