This MCP server provides natural language access to Gaudio Lab's Audio AI API for audio/video processing and lyrics synchronization.
Check API Key Info (gaudio_get_key_info): Retrieve remaining credits, permitted models, project name, and account status.
List Available Models (gaudio_list_models): Browse AI models filtered by category — stem (instrument separation), dme (dialogue/music/effects), or text_sync (lyrics sync).
Upload Files (gaudio_upload_file): Upload audio (WAV, FLAC, MP3, M4A), video (MOV, MP4), or text (TXT) files. Upload IDs are reusable for 72 hours.
Create & Monitor Jobs (gaudio_create_job / gaudio_get_job): Manually create processing jobs and poll for results; download URLs are valid for 48 hours.
All-in-One Audio Separation (gaudio_separate_audio): Upload and separate audio/video into stems (vocals, drums, bass, guitar, piano) or DME tracks (dialogue, music, effects) in a single step. Supports files up to 1GB/20 min (stem) or 10GB/200 min (DME).
All-in-One Lyrics Sync (gaudio_sync_lyrics): Upload an audio file and a UTF-8 lyrics text file to automatically align lyrics to timestamps, returning CSV and JSON reports with timestamps and confidence scores. Supports English, Korean, Japanese, and Simplified Chinese.
Provides audio processing capabilities through natural language commands, allowing users to separate vocals, instruments, dialogue, music, and effects from audio/video files, or sync lyrics to timestamps using Gaudio Lab's Audio AI API.
MCP server for Gaudio Lab Audio AI API. Separate vocals, instruments, dialogue, music, effects from any audio/video — or sync lyrics to timestamps — all through natural language in your AI tools.
Works with Claude, ChatGPT, Cursor, VS Code, GitHub Copilot, and any MCP-compatible client.
Sign up at Gaudio Developers
Create a project and get your API key from the dashboard
Related MCP server: IRCAM Amplify MCP Server
Add to your MCP client config:
{
"mcpServers": {
"gaudio": {
"command": "npx",
"args": ["-y", "@gaudiolab/mcp-developers"],
"env": {
"GAUDIO_API_KEY": "your-api-key-here"
}
}
}
}Then just ask in natural language:
"Separate the vocals from this file"
"Extract the dialogue from this video"
"Sync these lyrics to this song"
"What models are available?"
"How many credits do I have left?"
Tool | Description |
| Get API key info: credits, project, permitted models |
| List available AI models by category |
| Upload audio/video/text file (multipart, auto-chunked) |
| Create a processing job |
| Check job status and get download URLs |
| All-in-one: upload → process → download URLs |
| All-in-one lyrics sync with timestamps |
Model | Description | Type Options |
| Multi-instrument separation | vocal, drum, bass, electric_guitar, acoustic_piano |
| Super HQ vocal + accompaniment | vocal |
| Speech / noise removal | speech |
Max: 1GB / 20 min per file. Types can be combined (e.g. vocal,drum).
Model | Description |
| Dialogue extraction |
| Dialogue + vocals |
| Music + effects |
| Music + effects v1 |
| Music + effects v2 (high quality) |
| Music only |
| Effects only |
Max: 10GB / 200 min per file.
Model | Description | Languages |
| Lyrics line sync | en, ko, ja, zh-cn |
Max: 1GB / 10 min. Text: .txt (UTF-8), min 2 lines, max 60 chars/line.
Output: CSV (timestamp, lyric_text, confidence_score) + JSON report.
Type | Formats |
Audio | WAV, FLAC, MP3, M4A |
Video | MOV, MP4 (audio auto-extracted) |
Text | TXT (UTF-8) |
Output: MP3 (48kHz/320kbps) + WAV (same as input). Download URLs valid for 48 hours.
Upload file → Create job → Poll status → Get download URLsThe high-level tools (gaudio_separate_audio, gaudio_sync_lyrics) handle this entire flow automatically. Upload IDs are valid for 72 hours and can be reused across multiple jobs.
Gaudio Developers — API dashboard & key management
Documentation — Full API reference
Gaudio Lab — Company homepage
MIT
Create a processing job with an uploaded file. For Stem Separation models (gsep_music_hq_v1, gsep_music_shq_v1, gsep_speech_hq_v1), the 'type' parameter is required (e.g. 'vocal', 'vocal,drum'). For DME models, no type is needed. For Text Sync (gts_lyrics_line_v1), use gaudio_sync_lyrics instead.
Inputs: uploadId (required), model (required), type.
Check job status and get results. Status: 'waiting' (queued), 'running' (processing), 'success' (done, downloadUrl included), 'failed' (error). Download URLs expire after 48 hours.
Inputs: jobId (required), model (required).
Get API key information: description, creation date, status, permitted models, project name, and remaining credits (free + paid).
Inputs: no named parameters.
List available Gaudio AI models. Filter by category: 'stem' (instrument separation), 'dme' (dialogue/music/effects separation), 'text_sync' (lyrics sync).
Inputs: category.
All-in-one audio separation: upload file (or reuse uploadId) → create job → poll until done → return download URLs. For Stem Separation, provide 'type' (e.g. 'vocal', 'vocal,drum'). For DME Separation, no type needed. Supports WAV, FLAC, MP3, M4A, MOV, MP4.
Inputs: model (required), filePath, uploadId, type, +1 more.
All-in-one lyrics sync: upload audio + text files → create gts_lyrics_line_v1 job → poll → return CSV (timestamp, lyric_text, confidence_score) + JSON report URLs. Text file requirements: .txt format, UTF-8, minimum 2 lines, max 60 characters per line. Audio limit: 1GB / 10 minutes.
Inputs: language (required), audioFilePath, audioUploadId, textFilePath, +2 more.
Upload a local audio/video/text file to Gaudio servers. Handles multipart upload automatically (create → chunk upload → complete). The returned uploadId is valid for 72 hours and can be reused across multiple jobs. Supported formats: WAV, FLAC, MP3, M4A, MOV, MP4, TXT.
Inputs: filePath (required).
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 7 tools
Each tool has a distinct purpose: listing models, uploading files, creating jobs, checking job status, and two all-in-one wrappers plus API key info. The manual and wrapper tools are clearly differentiated by their descriptions, with the all-in-one tools explicitly labeled as such, leaving no ambiguity.
All tool names follow a consistent 'gaudio_' prefix with a verb_noun pattern in snake_case (list_models, upload_file, create_job, get_job, separate_audio, sync_lyrics, get_key_info). This is highly predictable and uniform.
Seven tools is well-scoped for a focused AI processing API. It covers the essential operations without unnecessary bloat, and each tool serves a clear function in the workflow, from listing models to managing jobs and retrieving results.
The tool set provides complete coverage for the domain: model discovery, file upload, job creation/status tracking, and two end-to-end workflows (separation and lyrics sync) plus account/key info. There are no obvious missing operations that would cause agent failures.
Audio AI tools: transcription with speakers, stems, noise removal, MIDI, speech, voices and music.
AI mixing and mastering: analyze your mixes, run DSP autofix, render stems, and master tracks.
Transcribe with speaker labels, split stems, remove noise, separate speakers, convert audio to MIDI.
Make AI Tracks, loops and sound effects, split stems, build drum kits and master songs.