Report Bug / Feature Request
AI Music Generator AI Song Generator AI Music Video Maker AI Beat Maker AI Lyrics Generator AI Jingle Generator AI Karaoke Maker Vocal Remover More →

AI Song Splitter

Commercial use OK @ item: inlistbox QPrintPreviewDialog Ba'a bukata shiga ba
Model:
+ GPT-5, Claude, Gemini

Danna ko kuma ka kwafa fayil ɗin sauti nan

MP3, WAV, FLAC, OGG, M4A
~1,000 tokens (~50/sec of audio)

Ana raba waƙa zuwa ɓangaren da ya dace...

Wannan zai iya ɗaukar sakan 30-60
KCharselect unicode block name
Advanced options
Result
Tokens running low. Get More Tokens
Want better results? Premium models (GPT-5, Claude, Gemini) deliver higher quality. View Plans

❤️ Ya so Free.ai? Ka gaya wa abokanka!

Ka yi rijista domin ka samu wata alaƙa ta shawara da kuma samun 25,000 tokens ga kowanne abokinka.

Shin kanã nufin ƙaryatãwa ne? Yi rajista kyauta don 5K tokens / rana + 10K kyauta
Sign Up Free

Processing your request...

Split any song into 4 stems with AI: vocals, drums, bass, other. MP3 / WAV in, ZIP out. Powered by Meta Demucs MIT, fully free.

Yadda ake amfani da shi AI Song Splitter

1
Enter your input

Ka rubuta rubutu, ka shigar da fayil, ko ka bayyana abin da kake so. Babu bukatar asusun.

2
Danna don ƙirƙira

Our AI processes your request in seconds using the best open-source models.

3
Download & share

Ka saukar, ka kwafe, ko ka raba sakamakonka. Kyauta ga amfanin kai da na kasuwanci.

Yi amfani da wannan kayan aiki ta hanyar API

Yi amfani da wannan kayan aiki daga lissafinka na kai tsaye. REST na ƙarshe mai haɗin kai na OpenAI, amincewa da token mai ɗaukar kaya, babu buƙatar SDK na musamman. Kudin token sun haɗu da haɗin yanar gizo.

API Documentation Get API Key 
curl -X POST https://api.free.ai/v1/music/generate/ \
  -H "Authorization: Bearer sk-free-..." \
  -H "Content-Type: application/json" \
  -d '{"prompt": "upbeat synthwave instrumental", "duration": 30}'

@ item: inlistbox

AI Music Generator
AI Song Generator
AI Music Video Maker
AI Beat Maker
AI Lyrics Generator
AI Jingle Generator
AI Karaoke Maker
Vocal Remover

AI Song Splitter — FAQ

It separates any song into 4 stems — vocals, drums, bass, and other (synths/piano/guitar/strings) — with AI. Each stem is its own WAV file. Same Demucs model used by Moises and Splitter.ai.

Vocal remover keeps everything except vocals (instrumental output). Isolate vocals does the opposite (acapella output). Song splitter gives you all four stems separately so you can mix and match. Same Demucs model under the hood.

A ZIP archive with 4 WAV files: vocals.wav, drums.wav, bass.wav, other.wav. Each is the same length and sample rate as the input, so they layer cleanly when re-mixed in a DAW.

MP3, WAV, M4A, FLAC, OGG, AIFF, and most common audio formats. Max upload 50 MB (about 5 minutes of MP3).

6-15 seconds per minute of input on our A100. A 3-minute song takes about 25-40 seconds.

Excellent on well-mixed studio tracks — vocals are nearly perfect, drums and bass very clean, "other" sometimes has a bit of crosstalk from neighboring stems. Lo-fi recordings, live shows, or heavily-effected tracks produce noisier separations.

Demucs uses a 4-stem decomposition (vocals/drums/bass/other) — the most popular pre-trained checkpoint. 6-stem variants exist (vocals/drums/bass/guitar/piano/other) but quality drops noticeably; 4-stem is the sweet spot.

Yes — the result page shows individual download buttons for vocals.wav, drums.wav, bass.wav, other.wav alongside the all-in-one ZIP.

Personal use (practice, study, remixes for non-commercial enjoyment) is generally fair-use OK. Sampling, publishing, or commercially releasing stems requires the song's sync / mechanical / sample license. You're responsible.

About 3,000 tokens per song, flat per-request (regardless of song length, since Demucs runs once on the whole track). Free daily-pool tokens cover most use.

Demucs (Meta) generally beats Spleeter (Deezer) on vocal-isolation quality and is comparable to Moises on the rest. Free.ai uses Demucs at the same quality tier as Moises Pro, but without the subscription.

Yes — POST audio to /v1/audio/separate/ with `mode=stems` to get all four stems back. Or specify `mode=vocals` / `mode=instrumental` for the single-stem variants. Docs at /api/.

Yi rajista kyauta don 10,000 tokens

Create Free Account

Ba'a bukata katin bashi ba

Yaya za ka rarraba wannan kayan aiki?

Ya so Free.ai? Ka gaya wa abokanka!