AIVoiceSeparator
💳 Pricing 🔌 API 🌐 ภาษาไทย

Vocal / Instrumental AI Separation

Turn any song into a backing track or clean vocals in about 6 minutes · free to try

—
🎚️ Studio —
—
🎚️ Studio quality
3-model ensemble (BS-Roformer + Mel-Roformer + MDX23C) + EBU-R128 loudnorm — ~5-6 min / song
⚡ SDR 12.97 dB · ~3 dB better than Demucs 🔒 No cloud · GPU in Thailand 🎯 hi-freq retention on par with vocalremover.org

How it works

  1. Upload — Drag an MP3 / WAV / M4A — up to 100 MB, up to 20 minutes
  2. Wait for AI — Studio pipeline (BS-Roformer + Mel-Roformer + MDX23C ensemble) takes ~5-6 minutes
  3. Download — You get vocals.wav + instrumental.wav (karaoke) separately

Free 3 songs (one-time) · join Patreon → Pro 6/day · audio stays in Thailand · local GPU

Frequently asked questions

Is AIVoiceSeparator really free?

Yes. Try 1 song free with no signup, then sign in with Google (free) for 3 free songs (one-time, not monthly) at full Studio quality (3-model AI ensemble + loudnorm). Patreon Pro raises the limit to 6/day.

How does AIVoiceSeparator compare to LALAL.AI or vocalremover.org?

Our 3-model ensemble (BS-Roformer + Mel-Roformer + MDX23C) measures SDR 12.97 dB — roughly 3 dB better than the open Demucs baseline. Output is EBU-R128 loudness-normalized so the stems sit naturally in any mix. Audio is processed on a private GPU in Thailand — never sent to a third-party cloud.

Do you store my uploaded songs?

Every job (input + outputs) is deleted automatically: after 24 hours if you're not signed in, or after 7 days if you are (so you can re-download it from your account). We never use your audio to train AI models, and we never share results between users — access is gated by an opaque job_id.

What audio formats do you support?

Input: MP3, WAV, M4A, FLAC, OGG, WebM, Opus. Max 100 MB, max 20 minutes. Output: MP3 320 kbps (default), WAV, or FLAC (lossless).

Can I separate a song directly from a YouTube link?

Yes. Paste a YouTube or SoundCloud URL and the server downloads the audio for you. For a TikTok or Instagram clip, save the video and upload the file (MP4/MOV) instead. You are responsible for having the rights to the content you process.

Can I get lyrics / subtitles from the song?

Yes. Enable the 'Generate lyrics' toggle before processing. We run Whisper on the isolated vocal stem and return SRT (subtitle), LRC (karaoke), and TXT (plain) files. Adds ~30 seconds to the run.