Sonicaura MCP README

sonicaura-mcp

Remote MCP server for audio stem separation, denoise, and reverb.

SonicAura processes audio using GPU-accelerated AI:

Stem separation — split a track into 2, 4, or 6 stems
- 2stems: vocals + no_vocals
- 4stems: vocals + drums + bass + other
- 6stems: vocals + guitar + bass + drums + piano + other
Denoise
- music_denoise: remove noise from music while keeping the instruments and vocals intact
- denoise: aggressive speech cleanup for podcasts / interviews / voiceovers
Reverb — add spatial reverb with presets: vocal_booth, studio_room, bathroom, concert_hall, church

Code

https://api.sonicaurastudio.com/mcp

Transport: http (Streamable HTTP) Auth: OAuth 2.0

Tool	Description
`list_audio_tools`	List available task types and metadata
`check_service_status`	Confirm service availability and credits
`get_upload_url`	Presigned URL for files larger than 1 MB
`upload_audio`	Base64 upload for files under 1 MB
`process_audio`	Submit a task (`music_denoise` \| `denoise` \| `reverb` \| `2stems` \| `4stems` \| `6stems`)
`extract_vocals`	Shortcut for `process_audio` with `task_type='2stems'` — extract vocals and instrumental
`check_task_status`	Poll a task
`get_my_credits`	Check remaining credits

Add the server to your MCP client config:

JSON Config

{
  "mcpServers": {
    "audio-process": {
      "type": "http",
      "url": "https://api.sonicaurastudio.com/mcp"
    }
  }
}

Then ask your client things like:

Prefer a visual interface? Use the same engine from the browser:

Vocal Remover & Karaoke — https://www.sonicaurastudio.com/tools/ai-vocal
Multitrack Splitter (2/4/6 stems) — https://www.sonicaurastudio.com/tools/vocal-separation

Processing uses credits. Get an account and credits at https://www.sonicaurastudio.com

MIT