LyRuno is a free AI audio separator for vocals, instruments and video dialogue, with local processing. Free plan; Professional plan from $19/month.
Researched and fact-checked by Bartu Cavusoglu · Updated October 26, 2026
LyRuno is a free AI audio separator that splits audio and video files into individual tracks. It can extract vocals, instruments and accompaniment from songs, and it can separate dialogue, music and sound effects from video content. The company describes the results as studio-quality and says no AI knowledge is needed to use it.
The product covers four scenarios. Music work includes karaoke, remixing and production. Video work covers editing, dubbing and post-production. Speech work removes background noise to isolate clean dialogue, and instrument work extracts or removes drums, bass, guitar and piano. The site is offered in ten languages.
LyRuno follows a three-step process. First, users import files. Video formats include MP4, MKV, FLV, AVI and WEBM, and audio formats include MP3, WAV, FLAC, AAC and M4A. Batch uploads are supported, and invalid files are filtered out automatically, so large folders can be added without manual sorting.
Next, users pick a separation scenario, such as vocal and accompaniment or instrument separation, and choose a model for it. Files can run individually or in batches, with options for length, GPU acceleration and output format. Finally, users open the results folder or listen in the built-in player. All processing happens locally, with no cloud upload.
The core capability is separation. LyRuno splits songs into vocals and accompaniment, pulls out bass, drums, piano and guitar, and separates dialogue, music and sound effects from video. It also removes whistling, clapping and similar sounds from vocals, and offers noise reduction and reverb removal for clearer sound.
Workflow tools support heavier use. Batch processing handles many files at once, GPU acceleration is detected automatically, and output can be saved in high-quality formats including WAV and FLAC. A built-in player lets users check results immediately. Several AI models are available per scenario, and the Professional plan adds more advanced ones.
LyRuno is a free AI audio separator. It extracts vocals, instruments and accompaniment from songs, and separates dialogue, music and sound effects from video content.
The Basic plan is $0 and described as free forever. The Professional plan is listed at $19 per month, discounted 35% from $29, and is pay-as-you-go with no automatic renewal.
The site says the community version is free forever and includes a variety of high-quality models for different separation scenarios. Professional models for harmonies, vocals, accompaniment and movie soundtracks require the paid plan.
No. The company states that all audio track separation is processed locally on the user's device and that no files need to be uploaded.
Video formats include MP4, MKV, FLV, AVI and WEBM. Audio formats include MP3, WAV, FLAC, AAC and M4A. Output in WAV and FLAC is supported.
Yes. Users can import multiple audio and video files, with invalid files filtered out automatically, and process them individually or in batches.
It suits musicians, producers, video editors and dubbing or post-production teams, as well as anyone who needs to isolate clean dialogue from interviews or speeches.
The sources do not list any integrations. LyRuno is presented as a standalone separation tool.