Skip to main content
Glama

create_cover_song

Transform songs into cover versions by applying different vocal styles or voices to original audio files using AI-powered voice conversion.

Instructions

Create a cover version of a song with a different voice or style

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
audio_urlYesURL of the original audio file
voice_idYesVoice model ID to use for the cover (use get_all_voices to find IDs)
webhook_urlNoURL for callback upon completion

Implementation Reference

  • The handler function that implements the core logic for the 'create_cover_song' tool. It validates inputs, makes a POST request to the MusicGPT API '/cover' endpoint, and returns the task details with instructions for status checking.
    private async handleCreateCover(args: any) {
      if (!args.audio_url || !args.voice_id) {
        throw new McpError(ErrorCode.InvalidParams, "audio_url and voice_id are required");
      }
    
      const response = await this.axiosInstance.post("/cover", {
        audio_url: args.audio_url,
        voice_id: args.voice_id,
        webhook_url: args.webhook_url,
      });
    
      return {
        content: [
          {
            type: "text",
            text: `Cover song creation started!\n\n${JSON.stringify(response.data, null, 2)}\n\nUse get_conversion_by_id with the task_id to check the status.`,
          },
        ],
      };
    }
  • The input schema defining parameters for the create_cover_song tool: required audio_url and voice_id, optional webhook_url.
    inputSchema: {
      type: "object" as const,
      properties: {
        audio_url: {
          type: "string",
          description: "URL of the original audio file",
        },
        voice_id: {
          type: "string",
          description: "Voice model ID to use for the cover (use get_all_voices to find IDs)",
        },
        webhook_url: {
          type: "string",
          description: "URL for callback upon completion",
        },
      },
      required: ["audio_url", "voice_id"],
    },
  • src/index.ts:161-182 (registration)
    The tool definition object in the TOOLS array, which is returned by the listTools handler, registering the tool's name, description, and schema.
    {
      name: "create_cover_song",
      description: "Create a cover version of a song with a different voice or style",
      inputSchema: {
        type: "object" as const,
        properties: {
          audio_url: {
            type: "string",
            description: "URL of the original audio file",
          },
          voice_id: {
            type: "string",
            description: "Voice model ID to use for the cover (use get_all_voices to find IDs)",
          },
          webhook_url: {
            type: "string",
            description: "URL for callback upon completion",
          },
        },
        required: ["audio_url", "voice_id"],
      },
    },
  • src/index.ts:671-672 (registration)
    The switch case in the CallToolRequestSchema handler that routes calls to the create_cover_song tool to its handler function.
    case "create_cover_song":
      return await this.handleCreateCover(args);

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/pasie15/mcp-server-musicgpt'

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