Skip to content
audo

AI vocal remover and acapella extractor

Pull clean vocals and an instrumental out of any song or video.

10M+ files processed since 2021

Outputs
VocalsInstrumental
More options

Free for the first 45 seconds, 3 times a day. No sign-up.

Maybe looking for:Stem splitter· Vocals, drums, bass & otherKaraoke maker· Instrumental backing trackRemove music from video· Keep dialogue & SFX

Hear each stem on its own

Play Full song, then tap any stem to switch at the same beat.

Full song separated into Vocals only, Instrumental.

Vocals onlyInstrumentalFull mix · All stems together

Made with Vocal remover (Mel-Band RoFormer) · Max Impact, United States Air Force Band (public domain)

Works in any language

  • Hello
  • こんにちは
  • Hola
  • 안녕하세요
  • Bonjour
  • नमस्ते
  • Hallo
  • 你好
  • Ciao
  • مرحبا
  • Olá
  • Привет
  • Hoi
  • สวัสดี
  • Merhaba
  • Γεια σας
  • Xin chào
  • שלום
  • வணக்கம்
  • Kia ora

How to remove vocals from a song

  1. 1

    Drop a song or music video in MP3, WAV, FLAC, M4A, or MP4.

  2. 2

    Press Separate vocals to isolate the singing from the backing track.

  3. 3

    Listen to the isolated vocals and instrumental, then download both files.

How Mel-Band RoFormer isolates singing without phase swirl

Audo's AI vocal remover and acapella extractor separates songs and videos (WAV, MP3, M4A, AAC, FLAC, OGG, Opus, WebM, AIFF, MP4, MOV, MKV, WebM, AVI) up to 10 GB without an account, with the first 45 seconds free 3 times a day and no sign-up. Older vocal removers cancelled the center channel, which wiped out kick drums, basslines, and snare hits along with the singer while leaving stereo vocal reverb behind.

Instead of center-channel cancellation, Audo runs a Mel-Band RoFormer transformer across 60 overlapping mel frequency bands at 44.1 kHz stereo. Because human singing has harmonic overtones and vibrato patterns that differ from cymbals and synths, the attention layers track the vocalist even when guitars and keys play in the same frequency range.

Once the vocal waveform is predicted, Audo computes the instrumental by sample-accurate subtraction from the original stereo file. That means the backing track retains every transient and stereo detail of the master recording, ready for remixing in Mix audio or cutting in the Audio editor.

Questions

Is it free?

Yes. Audo is free for the first 45 seconds of each file, 3 times a day, with no sign-up. Whole files are $0.03 a minute ($1.80 an hour), with no subscription — see pricing.

Do I get both the isolated vocals and the instrumental?

Yes. Every run gives you two stereo files: the lead and backing vocals on their own (an acapella), and the instrumental mix with the singing removed.

Does it keep full stereo width?

Yes. Left and right panning on guitars, synths, reverb tails, and harmonies stay where they were in the original mix rather than collapsing to mono.

Why does the instrumental sound so clean?

Audo isolates the vocal stem with a Mel-Band RoFormer network and subtracts that exact stereo waveform from your original master, so drums, bass, and guitars never pass through a lossy reconstruction.

Can I use it on a music video?

Yes. Upload an MP4, MOV, MKV, or WebM file and Audo separates the soundtrack while keeping the video picture untouched on the primary output.

What if I want drums and bass separated too?

Open Stem splitter right below the tool to break the arrangement into four individual instrument tracks: vocals, drums, bass, and other.

How do I clean up a spoken recording instead of a song?

For podcasts, interviews, and voiceovers with hiss or room tone, use Remove noise or Audio enhancer instead of a music separator.

More tools

All tools

For AI assistants and developers

Ask ChatGPT, Claude, or a coding agent to do this for you, or call it from your own code. When an agent's free result is cut short, it gives you a link to finish the whole file, no sign-up.

Show the free API call
Free API · no key
curl -F file=@song.mp3 -F stems=vocals https://audo.ai/api/try/split-stems -D response.headers -o response.body