Audio identification services

Automatic music file tag correction. Music catalog reconciliation and cross-referencing. 100% open source.

Automatic music file tagging

AcoustID can be used for adding an automatic tagging feature to music players or music library organization applications. It can identify unknown audio files by searching in a large public database of audio fingerprints. Once it identifies an audio file, it can suggest the correct tags, for which it uses high quality metadata from the open MusicBrainz database.

Thanks to the integration with MusicBrainz, it is also possible for applications to request additional metadata from either MusicBrainz itself or other services supporting MusicBrainz identifiers like the Cover Art Archive to get cover art images.

Music catalog management

Clients with large music catalogs can use AcoustID for automatic or semi-automatic metadata management. It can be used to cross-reference music files with MusicBrainz identifiers and also other metadata providers compatible with MusicBrainz.

As an example, cross-referencing the music catalog with MusicBrainz artist identifiers can help solve the problem of multiple artists having the same name by avoiding the need to do text search on the artist name.

AcoustID can be also used for detecting duplicate music files during the ingestion process.

Technology

At the core of AcoustID is an efficient algorithm for extracting audio fingerprints, called Chromaprint. The algorithm is optimized specifically for matching near-identical audio streams, which allows the audio fingerprints to be very compact and the extraction process to be fast. For example, it takes less than 100ms to process a two minute long audio file and the extracted audio fingerprint is just 2.5 KB of binary data.

AcoustID contains a large crowd-sourced database of such audio fingerprints together with additional information about them, such as the song title, artist or links to the MusicBrainz database. You can send an audio fingerprint to the AcoustID service and it will search the database and return you information about the song. We use a custom database for indexing the audio fingerprints to make the search very fast.

All of this is 100% open source and the database is available for download.

Pricing

The AcoustID service is free to use in non-commercial applications. If you want to use the service in a commercial product, please subscribe to one of the plans below. All plans come with a free trial. You are not charged for the first 10k searches. If you don't need more than that, you can use the service for free!

OPEN SOURCE

free

  • unlimited searches
  • 3 requests/second
  • no free trial needed ☺
LEARN MORE

SMALL

€50/month

  • 1 million searches
  • no rate limiting
  • free trial (10k searches)

MEDIUM

€100/month

  • 15 million searches
  • no rate limiting
  • free trial (10k searches)

LARGE

€500/month

  • 150 million searches
  • no rate limiting
  • free trial (10k searches)

The subscription is paid monthly for the service provided in the previous month. You can easily cancel your subscription at any time. We do not provide refunds.

If you are not sure which plan is right for your application, you would like a custom plan or need any help with your subscription, please contact us at [email protected].

Also, if you are a single developer and the plans are too expensive for you, feel free to get in touch, explain your situation and I'm sure we can figure something out.

The original AcoustID project was started in 2010 by Lukáš Lalinský with the goal of creating a completely open source platform for audio identification. The primary use case for the project was music file tagging in MusicBrainz Picard, but since then, it has been integrated in over one hundred other applications and used by thousands of individual users. In addition to being the first open source technology for audio identification, AcoustID also the first to make a large database of audio fingerprints freely available. Right now, it contains over 30 million audio fingerprints, with almost 10 million of them being mapped to the MusicBrainz database for very accurate metadata.

In 2016, Lukáš started a company to provide better support for both existing and new commercial users of the AcoustID service, to provide funding for the open source project to make sure it keeps growing, but also to expand the options of what's possible with the AcoustID technology. We are currently developing new audio identification solutions. Expect more open source goodness soon!