AudioShake

API

Stem separation API for vocals and instruments, or dialogue, music and effects

Price: 10 free credits, then prepaid credits
Access: API key (x-api-key header)

About

Hosted separation API for music and media. A task runs models on a URL or upload: vocals, lead or backing vocals, drums, drum kit, bass, guitar, piano, keys, strings, wind; dialogue, music and effects for dubbing; per-speaker splits; time-synced lyrics. Billed in credits per minute.

What you can do with it

Split a song into vocals, drums, bass, guitar, piano, strings and wind stems
Separate dialogue from music and effects in film, TV or podcast audio for dubbing
Make karaoke tracks with an instrumental stem and time-synced lyrics in one task

Get started

Sign up at dashboard.audioshake.ai to get 10 free credits
Create an API key under Settings > API Keys
Create a task with one target per stem, then poll it or use a webhook

Example

curl -X POST "https://api.audioshake.ai/tasks" \
  -H "Content-Type: application/json" \
  -H "x-api-key: $AUDIOSHAKE_API_KEY" \
  -d '{
    "url": "https://demos.audioshake.ai/demo-assets/shakeitup.mp3",
    "targets": [
      { "model": "vocals", "formats": ["wav"] },
      { "model": "instrumental", "formats": ["wav"] }
    ]
  }'

Details

Hosting: Hosted service
Available in: Worldwide
MCP server: None