# worldveil/dejavu

Audio fingerprinting and recognition in Python

Repository: https://github.com/worldveil/dejavu
Canonical: https://ross.abutalabs.com/products/worldveil-dejavu
Language: Python
License: MIT
License Family: permissive
Last push: 2024-04-22T19:23:00+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 4670, "days_push": 863, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 6784, forks 1464 (observed 2026-08-28T04:09:48.581874+00:00)

## What it is
Dejavu is a Python library that fingerprints audio files and recognizes songs by matching recorded microphone input or audio from disk against a database of fingerprints. It is designed for exact-signal matching with noise tolerance, not speech or voice recognition.

## Use cases
- identify which song is playing from a microphone recording
- build a Shazam-like audio recognition service
- fingerprint a music library into a database for matching
- match an audio clip against known recordings even with noise
- detect duplicate or known audio in media files

## When to choose
- you need to recognize specific songs or exact audio signals from recordings
- you want a self-hosted, database-backed audio fingerprinting pipeline in Python
- you need noise-tolerant matching of known audio rather than transcription

## When to avoid
- you need speech-to-text or voice/speaker recognition
- you need real-time recognition at large commercial scale
- you want a turnkey mobile app rather than a Python library

## Facets
- artifact type: library
- maturity: maintenance
- function: audio-processing, search-engine, database
- domain: machine-learning, developer-tools
- platform: python, cross-platform
- tags: audio-fingerprinting, shazam-like, song-recognition, signal-processing, audio, docker

## Member repositories
- worldveil/dejavu (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:48.581874+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:42:21.661167+00:00, confidence not recorded.
  - readme: https://github.com/worldveil/dejavu (fetched 2026-08-28T04:09:48.581874+00:00, sha 69ba130c5e14)
- Data as of 2026-08-30T08:39:29.467469+00:00.