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.
| Name | Required | Description | Default |
|---|---|---|---|
| uploadId | Yes | Upload ID from gaudio_upload_file (used as audioUploadId) | |
| model | Yes | Model name (e.g. gsep_music_hq_v1, gsep_dme_dtrack_v1) | |
| type | No | Stem type(s), comma-separated. Required for Stem Separation models. e.g. 'vocal', 'vocal,drum,bass' |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Given no annotations, the description discloses key behavioral traits: the conditional requirement of the 'type' parameter based on model selection. It does not mention potential side effects, authentication needs, or error cases, but the provided information is sufficient for safe usage.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise with three sentences, each serving a purpose: stating the action, explaining parameter rules for different models, and providing an alternative tool. No extraneous information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With three parameters, no output schema, and no annotations, the description adequately explains parameter usage and conditional logic. It could optionally mention the output (e.g., job ID), but the current information is sufficient for the agent to invoke the tool correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. The description adds value by explaining the conditional requirement of the 'type' parameter and providing examples (e.g., 'vocal', 'vocal,drum,bass'), which go beyond the schema's description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Create a processing job with an uploaded file', identifying the specific verb and resource. It distinguishes from sibling tools by mentioning that for Text Sync, one should use gaudio_sync_lyrics instead.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit guidance on when to use this tool: for Stem Separation models, the 'type' parameter is required; for DME models, no type is needed; and for Text Sync, a different tool is recommended. This effectively tells the agent when to use and when not to use the tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Check job status and get results. Status: 'waiting' (queued), 'running' (processing), 'success' (done, downloadUrl included), 'failed' (error). Download URLs expire after 48 hours.
| Name | Required | Description | Default |
|---|---|---|---|
| jobId | Yes | Job ID from gaudio_create_job or gaudio_separate_audio | |
| model | Yes | Model name used to create the job |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It discloses the polling nature, status states, and URL expiration, but does not mention authentication or request limits. It is adequate but not comprehensive.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise sentences pack the essential information: purpose, status states, and download URL expiration. No superfluous content.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple status-checking tool with two required parameters and no output schema, the description covers key aspects: status enumeration, URL expiration, and result availability. Could mention that results are included on success, but overall complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Input schema covers both parameters with descriptions (100% coverage). The description adds value by indicating that jobId comes from specific creation tools (gaudio_create_job or gaudio_separate_audio), which is helpful context beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose as checking job status and retrieving results, and lists possible statuses with outcomes. This distinguishes it from sibling tools like gaudio_create_job (creation) or gaudio_list_models (listing).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage after job creation but does not explicitly state when to use this tool versus alternatives or provide exclusions. It does include a useful note about download URL expiration.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get API key information: description, creation date, status, permitted models, project name, and remaining credits (free + paid).
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so the description carries full burden. It states the tool retrieves information, implying a safe, read-only operation, but does not disclose potential side effects (e.g., authentication requirements or rate limits). Given the tool's simplicity, this is minimally adequate but not rich.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that front-loads the purpose and enumerates key output fields. No wasted words; every element contributes to clarity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description fully covers return values by listing all relevant fields. With zero input parameters and a simple read operation, the description is complete and sufficient for an agent to use the tool correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has zero parameters, so the description need not explain them. It adds value by listing the returned fields, helping the agent understand what the tool provides. Baseline is 4 for no parameters.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly identifies the tool's action ('Get') and the resource ('API key information'), listing specific attributes (description, creation date, status, etc.). It distinguishes itself from sibling tools like gaudio_create_job and gaudio_separate_audio, which handle different operations.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies a simple read operation but lacks explicit guidance on when to use this tool versus alternatives. No exclusions or prerequisites are mentioned, though the context of sibling tools suggests it's for retrieving key metadata.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List available Gaudio AI models. Filter by category: 'stem' (instrument separation), 'dme' (dialogue/music/effects separation), 'text_sync' (lyrics sync).
| Name | Required | Description | Default |
|---|---|---|---|
| category | No | Filter by category: all (default), stem, dme, or text_sync | all |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the burden. It mentions listing and filtering but does not disclose read-only nature, authentication, or rate limits. The behavior is implied but not explicit.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single, front-loaded sentence that efficiently conveys purpose and parameter usage with no wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given low complexity (one optional parameter, no output schema), the description adequately covers purpose and filtering. It does not explain output format, but this is acceptable for a simple list tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with descriptions for each enum value. The description adds real-world meaning ('stem' = instrument separation) beyond the schema, aiding selection.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool lists Gaudio AI models and explains the filter categories. The verb 'list' and resource 'models' are precise, and it distinguishes from sibling tools like gaudio_create_job or gaudio_separate_audio.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for viewing models by category but lacks explicit when-to-use or when-not-to-use guidance. However, the context of sibling tools provides clarity on distinct purposes.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
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.
| Name | Required | Description | Default |
|---|---|---|---|
| filePath | No | Path to local audio/video file. Either filePath or uploadId is required. | |
| uploadId | No | Existing uploadId to reuse (skips upload). Valid for 72 hours. | |
| model | Yes | Model name (e.g. gsep_music_hq_v1, gsep_dme_dtrack_v1) | |
| type | No | Stem type(s) for Stem Separation models. e.g. 'vocal', 'vocal,drum' | |
| pollInterval | No | Polling interval in seconds (default: 10) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavior. It explains the multi-step workflow and the polling interval parameter. However, it does not mention potential side effects, rate limits, error handling, or what happens on failure. The polling behavior is partially described but lacks details on completion criteria.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, front-loaded with the core purpose, followed by targeted details. No redundant or extraneous information. Every sentence adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description covers the full workflow, input parameters, and output (download URLs). It lists supported file formats and differentiates between modes. Without an output schema, it provides enough context for basic usage, though it could include more detail on result structure or error scenarios.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, and the description adds context: it clarifies that filePath and uploadId are alternatives, explains the conditional use of 'type' for Stem Separation, and notes the default pollInterval. This goes beyond the schema's individual parameter descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the tool's purpose as an all-in-one audio separation workflow (upload, create job, poll, download). It distinguishes between Stem Separation and DME Separation modes and lists supported file types, making it highly specific and distinct from siblings.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides clear guidance on when to provide 'type' for Stem Separation and that DME Separation doesn't need it. Also explains upload options (filePath vs uploadId). However, it does not explicitly address when NOT to use this tool or compare it to sibling tools like gaudio_create_job or gaudio_upload_file.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
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.
| Name | Required | Description | Default |
|---|---|---|---|
| audioFilePath | No | Path to local audio file. Either audioFilePath or audioUploadId required. | |
| audioUploadId | No | Existing audio uploadId to reuse. | |
| textFilePath | No | Path to local .txt lyrics file. Either textFilePath or textUploadId required. | |
| textUploadId | No | Existing text uploadId to reuse. | |
| language | Yes | Language of the lyrics: en (English), ko (Korean), ja (Japanese), zh-cn (Chinese Simplified) | |
| pollInterval | No | Polling interval in seconds (default: 10) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so the description bears full responsibility. It discloses the workflow (upload, create job, poll, return results) and constraints (size, format). However, it omits behavioral details like whether resources persist, authorization needs, or side effects. For a tool that creates jobs, this is adequate but not exhaustive.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single paragraph that front-loads the purpose and then lists requirements. It is concise with no wasted words, though a bulleted list could improve readability. It earns a 4 for efficiency and clarity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 6 parameters, no output schema, and no annotations, the description covers the essential process, input constraints, and deliverable format (CSV + JSON report URLs). It lacks details about polling mechanics or report structure, but is substantially complete for an agent to invoke the tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Input schema has 100% coverage with descriptions for all 6 parameters. The description adds workflow context (e.g., 'upload audio + text files' maps to the file path/upload ID parameters) but does not significantly extend parameter meaning beyond the schema. A baseline of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose with a specific verb+resource: 'upload audio + text files → create gts_lyrics_line_v1 job → poll → return CSV + JSON report URLs'. This distinguishes it from sibling tools like gaudio_create_job which likely only creates a job without the upload+sync workflow.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides usage constraints (text format, audio limits) but lacks explicit guidance on when to use this tool versus alternatives (e.g., manually calling gaudio_upload_file and gaudio_create_job). It implies the all-in-one nature but does not state comparative benefits or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
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.
| Name | Required | Description | Default |
|---|---|---|---|
| filePath | Yes | Absolute path to the local file to upload |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It discloses multipart upload behavior, uploadId validity (72 hours), reusability across jobs, and supported formats. This is good transparency for a file upload action.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences clearly front-loading the purpose and then adding key details. Every sentence adds value without redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Covers upload process, reusability, formats, and validity. However, does not explicitly state what the tool returns (e.g., uploadId). Minor gap but overall sufficient for an upload tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema already describes filePath as 'Absolute path to the local file'. The description adds context about supported formats but does not significantly enhance parameter understanding beyond the schema. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it uploads a local audio/video/text file to Gaudio servers, with automatic multipart upload. This verb+resource combination is specific and distinct from sibling tools that deal with jobs, models, etc.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explains automatic multipart upload and uploadId reuse, but does not explicitly specify when to use this tool versus alternatives like gaudio_create_job. Usage is implied but not clearly guided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tools are mostly distinct with clear purposes, though there is intentional overlap between granular workflow tools (upload_file/create_job/get_job) and high-level 'all-in-one' wrappers (separate_audio, sync_lyrics). Descriptions mitigate confusion by explicitly labeling the latter as all-in-one and specifying when to use each path.
All tools follow a consistent gaudio_verb_noun pattern using snake_case. Verbs (create, get, list, separate, sync, upload) and nouns (job, models, audio, lyrics, file) are applied uniformly throughout the set.
Seven tools is well-scoped for an audio processing API, providing granular primitives (upload, create, get) alongside convenience wrappers for common workflows (separation, lyrics sync), plus metadata tools (models, key info) without bloat.
Covers the full job lifecycle (upload, create, get/status) for the three model categories mentioned (stem, dme, text_sync). Minor gaps exist for operational completeness (no list_jobs, cancel_job, or delete operations), but core CRUD and domain-specific workflows are present.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
AI mixing and mastering: analyze your mixes, run DSP autofix, render stems, and master tracks.
AI music studio: song generation with vocals, covers, stems, voice conversion, mastering, editing.
Convert projects between Logic, Ableton, FL Studio and REAPER; generate, separate, transcribe
Audio mastering for AI agents: LUFS/True Peak targets, Suno/Udio AI-fingerprint removal.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/gaudiolab-mcp/gaudio-developers-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
