SoundsLike – AI-based Tagging and Search for Large Music Catalogs

Unlock the full potential of your music archive with SoundsLike, the ultimate solution for effective and automatic curation, tailored metadata enrichment, and powerful similarity search.

SoundsLike revolutionizes your music archive by transforming it into a fully indexed and searchable database. With our advanced AI technology, you can annotate and organize music tracks from any source using the same principles. Say goodbye to duplicate content and easily add new tracks to your collection.

From AI research directly into application

Our team of experts combines extensive knowledge in audio signal processing and machine learning to deliver a comprehensive toolset of music analysis solutions. From extracting single notes to capturing harmonic progressions, instrumentation, genres, and moods, SoundsLike can extract a wide variety of valuable information from your audio data. You have full control to choose the categories and data that fit your specific use case.

Your music archive is your treasure – let’s uncover it together.

Your music archive is a treasure trove waiting to be discovered. With SoundsLike, our AI technology analyzes your existing music archive, understands your specific metadata and category system, and optimizes it to suit your needs. Whether you have a diverse production music library or an extensive classical music archive, SoundsLike listens, learns, and identifies the appropriate categories and subcategories for your music catalog.

Unlock New Possibilities with SoundsLike

Faster Music Tagging

Say goodbye to costly and incomplete manual tagging. SoundsLike Annotation classifies and annotates your music archive automatically, saving you time and resources while opening up new search possibilities.

Intuitive Search Options

Search using a sample track, refine the results using filters or use categories and tags – SoundsLike provides you with various search options that you can combine as you wish for a perfect search result, depending on the use case.

One stop search

With SoundsLike, you can make catalogs and archives from different sources searchable with just a single click. SoundsLike Annotation automatically completes and unifies existing metadata from various sources, streamlining your music organization.

Music Replacement

Need an alternative musical background for your video? SoundsLike Similarity helps you find a selection of songs in your database that match the mood, genre, and tempo of your sample track in just seconds.

Enhance Music Production

Professional music producers use search engines to find sounds, beats and loops that match a particular music production. SoundsLike takes it a step further by finding loops and beats that perfectly complement your production based on a sample track.

SoundsLike Annotation und SoundsLike Similarity

SoundsLike consists of two powerful components: SoundsLike Annotation and SoundsLike Similarity. SoundsLike Annotation enriches your music archive with customized metadata, making it fully searchable. SoundsLike Similarity automatically finds similar-sounding music tracks within your archive. These components can be combined seamlessly, allowing you to search your archive using metadata tags or even an audio sample, and then filter and refine your search results with ease.

Availability and support

The SoundsLike Annotation and SoundsLike Similarity components are licensable as REST API services and C++ libraries for Windows and Linux for integration into existing systems.

In addition, we also offer stand-alone solutions, with which you can obtain result files in XML or JSON format for further processing.

  • Runs on-site or on cloud providers such as AWS, Azure, or Google Cloud
  • Services available as both executables and Docker containers

We support you in analyzing, advising and adapting SoundsLike to your specific use case.

The annual license fee includes support for integration and maintenance as well as updates. We are open to application-specific enhancements and can provide you with an individualized offer tailored to your needs.

Contact us for a trial version and a custom-fit solution for your specific use case.

SoundsLike FAQ

SoundsLike Annotation

What metadata categories does SoundsLike use?

SoundsLike offers a comprehensive set of standard categories, including:

  • Speech Detector: Speech, NoSpeech
  • Music Detector: Music, NoMusic
  • Genre: Classical, Country, Electronica, Jazz, Latin, Pop, Rap, Rock, Soul, Speech
  • Emotion: Anxious, Depressed, Exuberant, Content
  • Valence: High, Low
  • Arousal: High, Low
  • Perceived Tempo: Fast, MidFast, Mid, MidSlow, Slow
  • Beats: per minute e.g. 120 bpm
  • Key: C to B
  • Color: Bright, Dark
  • Texture: Hard, Soft
  • Instrumental Density: Full, Sparse
  • Distortion: Clean, Gained, Overdrive, XXL
  • Dynamic: Changing, Continuous
  • Percussive: Nonpercussive, Percussive
  • Synthetic: Acoustic, Synthetic
  • Loop-specific Genres: Bass_music, Breaks, Cinematic, Disco, Hard_dance, Hip_hop, House, Idm, Pop, Blues, Country, Downtempo, Drum_and_bass, Funk, Reggae, Soul_and_rnb, Synthwave, Rock, Techno, Trance, Trap, World
  • Loop-specific Instruments: Bass, Cymbal, Drum, Effects, Guitar, Keyboard, Mallet, Mixed, Percussion, String, Synth, Vocal, Wind_and_brass
Can the categories be customized and changed?

SoundsLike provides the flexibility to use our standard metadata categories as a starting point and customize them based on your specific application – or use your very own category system as a basis. You can easily configure and compile categories to meet your unique requirements.

Can SoundsLike support archives consisting exclusively of electronic or classical music?

Absolutely! SoundsLike's AI technology can analyze your music archive and adapt to your specific metadata and category system. Together with our experts, you can develop a custom-fit category system optimized for your electronic or classical music archive.

Optionally, the AI model can also be trained using your existing music files and metadata to automatically annotate and assign new content.

What computing power is needed to annotate an archive?

The classification time for a 4-minute song with the default configuration takes around 8-10 seconds on an ordinary PC. The classification process supports multithreading/parallelization, resulting in reduced classification times on 8-/16-core CPUs (e.g., annotating 1000 songs in approximately 10 minutes on a 16-core CPU). Custom configurations may lead to different runtimes. Deep learning-based classification variants can be accelerated by GPUs.

How fast is my database prepared?

1000 songs on 16-core CPU are annotated in about 10 minutes.

What is the average computation time needed for Similarity Search in 1 million songs?

A desktop computer can perform Similarity Search in a database with 1 million songs in approximately 2 seconds. Recommendations can be precalculated regularly for an existing archive, ensuring immediate retrieval. Even when new titles are added, the similarity relations of the existing data remain stored in the cache and are updated in the background based on the new titles, providing near real-time access to recommendation lists.

How many music tracks are output by Similarity Search?

The number of similar music titles output for a search query can be individually set in the configuration. You can specify whether you want the most similar title only or a list of several hundred titles sorted in descending order of similarity to the source title.

How to combine SoundsLike Annotation and SoundsLike Similarity?

The results of Similarity Search can be further filtered using the annotated metadata from SoundsLike Annotation. These filters can be combined as desired, allowing you to refine your search results based on specific criteria. For example, you can search for jazz music with a slow tempo and vocals.


Research topic

Automatic Music Analysis


Reference project

Jamahook – AI Sound Matching


Artikel / 8.8.2022

Music Analysis Technologies

In Fraunhofer Digital Media's latest trend brochure you can read how our AI-based music analysis technologies can help broadcasters.