MusicGPT MCP Server

Instructions

Implementation Reference

• src/index.ts:921-940 (handler)

  The main handler function that executes the text_to_speech tool. Validates inputs, makes API call to /TextToSpeech endpoint, and returns task status information.

  private async handleTextToSpeech(args: any) {
    if (!args.text || !args.voice_id) {
      throw new McpError(ErrorCode.InvalidParams, "text and voice_id are required");
    }
  
    const response = await this.axiosInstance.post("/TextToSpeech", {
      text: args.text,
      voice_id: args.voice_id,
      webhook_url: args.webhook_url,
    });
  
    return {
      content: [
        {
          type: "text",
          text: `Text-to-speech conversion started!\n\n${JSON.stringify(response.data, null, 2)}\n\nUse get_conversion_by_id with the task_id to check the status.`,
        },
      ],
    };
  }

• src/index.ts:229-250 (schema)

  Input schema and metadata definition for the text_to_speech tool, including required parameters text and voice_id.

  {
    name: "text_to_speech",
    description: "Convert text to speech using AI voices",
    inputSchema: {
      type: "object" as const,
      properties: {
        text: {
          type: "string",
          description: "Text to convert to speech",
        },
        voice_id: {
          type: "string",
          description: "Voice model ID to use (use get_all_voices to find IDs)",
        },
        webhook_url: {
          type: "string",
          description: "URL for callback upon completion",
        },
      },
      required: ["text", "voice_id"],
    },
  },

• src/index.ts:679-680 (registration)

  Registration of the text_to_speech handler in the central tool dispatch switch statement within CallToolRequestSchema handler.

  case "text_to_speech":
    return await this.handleTextToSpeech(args);

• src/index.ts:50-50 (helper)

  Enum constant 'TEXT_TO_SPEECH' used in conversionType for get_conversion_by_id helper tool to query TTS task status.

  "TEXT_TO_SPEECH",