Skip to main content
Glama
gaudiolab-jp

gaudio-developers-mcp

Official

gaudio_create_job

Create audio processing jobs for stem separation or DME track isolation using uploaded files. Configure stem types like vocals or drums for separation models.

Instructions

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.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
uploadIdYesUpload ID from gaudio_upload_file (used as audioUploadId)
modelYesModel name (e.g. gsep_music_hq_v1, gsep_dme_dtrack_v1)
typeNoStem type(s), comma-separated. Required for Stem Separation models. e.g. 'vocal', 'vocal,drum,bass'

Implementation Reference

  • The main handler function for gaudio_create_job. Registers the tool with MCP server and implements the business logic: validates model exists, checks if 'type' is required for the model, builds params, calls client.createJob(), and returns the jobId with status.
    export function registerCreateJob(server: McpServer, client: GaudioClient) {
      server.tool(
        "gaudio_create_job",
        "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.",
        {
          uploadId: z.string().describe("Upload ID from gaudio_upload_file (used as audioUploadId)"),
          model: z.string().describe("Model name (e.g. gsep_music_hq_v1, gsep_dme_dtrack_v1)"),
          type: z
            .string()
            .optional()
            .describe("Stem type(s), comma-separated. Required for Stem Separation models. e.g. 'vocal', 'vocal,drum,bass'"),
        },
        async ({ uploadId, model, type }) => {
          const modelInfo = getModel(model);
          if (!modelInfo) {
            return {
              content: [{ type: "text" as const, text: `Unknown model: ${model}. Use gaudio_list_models to see available models.` }],
              isError: true,
            };
          }
    
          if (modelInfo.typeRequired && !type) {
            return {
              content: [
                {
                  type: "text" as const,
                  text: `Model ${model} requires a 'type' parameter. Options: ${modelInfo.typeOptions?.join(", ")}`,
                },
              ],
              isError: true,
            };
          }
    
          const params: Record<string, unknown> = { audioUploadId: uploadId };
          if (type) params.type = type;
    
          const { jobId } = await client.createJob(model, params);
    
          return {
            content: [
              {
                type: "text" as const,
                text: JSON.stringify({ jobId, model, status: "created" }, null, 2),
              },
            ],
          };
        },
      );
    }
  • The API client helper method that makes the actual HTTP POST request to create a job. Sends request to /{model}/jobs endpoint with params and returns the jobId from the response.
    async createJob(
      model: string,
      params: Record<string, unknown>,
    ): Promise<{ jobId: string }> {
      const res = await this.request("POST", `/${model}/jobs`, params);
      return { jobId: res.resultData?.jobId as string };
    }
  • src/index.ts:29-29 (registration)
    Where the gaudio_create_job tool is registered with the MCP server by calling registerCreateJob with the server and client instances.
    registerCreateJob(server, client);
  • src/index.ts:1-13 (registration)
    Import statements and setup for tool registration, including the import of registerCreateJob from ./tools/create-job.js on line 8.
    #!/usr/bin/env node
    
    import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js";
    import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";
    import { GaudioClient } from "./api/client.js";
    import { registerListModels } from "./tools/list-models.js";
    import { registerUploadFile } from "./tools/upload-file.js";
    import { registerCreateJob } from "./tools/create-job.js";
    import { registerGetJob } from "./tools/get-job.js";
    import { registerSeparateAudio } from "./tools/separate-audio.js";
    import { registerSyncLyrics } from "./tools/sync-lyrics.js";
    import { registerGetKeyInfo } from "./tools/get-key-info.js";
  • Zod schema definition for gaudio_create_job tool parameters: uploadId (required string), model (required string), and type (optional string for stem types).
    {
      uploadId: z.string().describe("Upload ID from gaudio_upload_file (used as audioUploadId)"),
      model: z.string().describe("Model name (e.g. gsep_music_hq_v1, gsep_dme_dtrack_v1)"),
      type: z
        .string()
        .optional()
        .describe("Stem type(s), comma-separated. Required for Stem Separation models. e.g. 'vocal', 'vocal,drum,bass'"),
    },
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description carries full burden. It adds valuable conditional logic for parameter requirements, but lacks disclosure about operational behavior: async nature of jobs, need to poll status via gaudio_get_job, credit consumption, or error handling. Does not contradict any annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Highly efficient three-sentence structure. Front-loaded with core purpose ('Create a processing job'), followed by conditional parameter guidance, then sibling redirection. No wasted words; every clause provides actionable information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Adequate for parameter configuration, but given the presence of gaudio_get_job as a sibling and the async nature of job processing, the description should mention that created jobs are asynchronous and require status checking via the get_job tool. No output schema exists to compensate.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% (baseline 3). Description adds significant value by providing concrete model examples (gsep_music_hq_v1), explaining the conditional requirement logic for the 'type' parameter, and clarifying uploadId sourcing from gaudio_upload_file.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Clear specific verb ('Create') + resource ('processing job') + input ('uploaded file'). Distinguishes from gaudio_sync_lyrics by explicitly redirecting text sync tasks there, and implies distinction from gaudio_upload_file by requiring an uploadId from that tool.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Excellent explicit guidance: states when 'type' parameter is required (Stem Separation models) vs not needed (DME models), provides concrete examples ('vocal', 'vocal,drum'), and explicitly names alternative tool 'gaudio_sync_lyrics' for text sync use cases.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/gaudiolab-jp/gaudio-developers-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server