Developers

Music Recognition API, CLI and MCP Server

Identify songs and read BPM, musical key and Camelot codes from your terminal, from an MCP client, or straight from your own code. Free, no API key, open source.

One command, the whole analysis

Every command that names a track accepts a search phrase as readily as an ISRC.

$ songfinder analyze "strobe deadmau5"

I Remember (Strobelight Edit) — deadmau5
Strobelite Seduction (2013)
ISRC:           USUS10800096

Tempo:          128 BPM
Key:            B Minor (Camelot 10A, Open Key 3m)
Mixes with:     10B, 9A, 11A
Energy:         59%
Danceability:   66%

What the API gives you

The same endpoints that power this site, open to any client.

Recognition

From a YouTube, TikTok, Instagram, SoundCloud, Bilibili or X link, from any direct media URL, or from an audio file. A chain of engines runs in order until one matches.

Acoustic analysis

Tempo, musical key with its Camelot wheel position and compatible keys, plus energy, danceability, valence, acousticness, instrumentalness, liveness, speechiness and loudness.

Neighbour search

Tracks that sound like a given one, optionally restricted to keys that mix cleanly with it — what you want when the output is a DJ set rather than a list.

No API key, no account

No signup and no rate card. Song Finder runs recognition through its own self-deployed API and rate-limits requests per IP to keep the service stable; analysis endpoints allow roughly one call every one to five seconds.

Open source

All three clients are MIT licensed and developed in the open. Issues and pull requests are welcome on any repository.

github.com/songfinder-dev

Prefer the browser?

Every capability here also runs as a web tool — no install, no terminal.

Identify a song