vocea_generate_audio

Instructions

Implementation Reference

• src/index.ts:109-133 (handler)

  Handler for the vocea_generate_audio tool. It extracts the required arguments (voice_id, text, language_code) and optional arguments (emotion, speaking_rate), calls the Vocea SDK's audios.generate() method, and returns a JSON response with id, audioUrl, durationSeconds, and characterCount.

  case "vocea_generate_audio": {
    const a = args as { voice_id: string; text: string; language_code: string; emotion?: string; speaking_rate?: number };
    const audio = await vocea.audios.generate({
      voice_id: a.voice_id,
      text: a.text,
      language_code: a.language_code,
      voice_setting: {
        emotion: (a.emotion as never) ?? "neutral",
        speakingRate: a.speaking_rate ?? 1.0,
      },
    });
    return {
      content: [
        {
          type: "text",
          text: JSON.stringify({
            id: audio.id,
            audioUrl: audio.audioUrl,
            durationSeconds: audio.durationSeconds,
            characterCount: audio.characterCount,
          }),
        },
      ],
    };
  }

• src/index.ts:30-47 (schema)

  Schema/registration definition for vocea_generate_audio in the ListToolsResponse. Defines the inputSchema with required properties: voice_id (string), text (string, max 10000 chars), language_code (string), and optional properties: emotion (enum of emotional tones), speaking_rate (number 0.5-1.5).

  {
    name: "vocea_generate_audio",
    description: "Convert text to speech using a Vocea voice. Returns an audio URL.",
    inputSchema: {
      type: "object",
      properties: {
        voice_id: { type: "string", description: "Voice UUID to use for synthesis" },
        text: { type: "string", description: "Text to convert to speech (max 10000 chars)" },
        language_code: { type: "string", description: "Language code, e.g. 'en', 'es', 'fr'" },
        emotion: {
          type: "string",
          enum: ["neutral", "happy", "sad", "angry", "fearful", "surprised", "disgusted", "whisper"],
          description: "Emotional tone (default: neutral)",
        },
        speaking_rate: { type: "number", description: "Speaking rate multiplier 0.5–1.5 (default 1.0)" },
      },
      required: ["voice_id", "text", "language_code"],
    },

• src/index.ts:28-100 (registration)

  The tool is registered with the MCP server via ListToolsRequestSchema, listing all six tools including vocea_generate_audio as part of the tools array.

  server.setRequestHandler(ListToolsRequestSchema, async () => ({
    tools: [
      {
        name: "vocea_generate_audio",
        description: "Convert text to speech using a Vocea voice. Returns an audio URL.",
        inputSchema: {
          type: "object",
          properties: {
            voice_id: { type: "string", description: "Voice UUID to use for synthesis" },
            text: { type: "string", description: "Text to convert to speech (max 10000 chars)" },
            language_code: { type: "string", description: "Language code, e.g. 'en', 'es', 'fr'" },
            emotion: {
              type: "string",
              enum: ["neutral", "happy", "sad", "angry", "fearful", "surprised", "disgusted", "whisper"],
              description: "Emotional tone (default: neutral)",
            },
            speaking_rate: { type: "number", description: "Speaking rate multiplier 0.5–1.5 (default 1.0)" },
          },
          required: ["voice_id", "text", "language_code"],
        },
      },
      {
        name: "vocea_list_voices",
        description: "List the authenticated user's cloned voices.",
        inputSchema: {
          type: "object",
          properties: {
            page: { type: "number", description: "Page number (default 1)" },
            limit: { type: "number", description: "Results per page (default 20)" },
          },
        },
      },
      {
        name: "vocea_list_public_voices",
        description: "List public community voices available for use.",
        inputSchema: {
          type: "object",
          properties: {
            page: { type: "number" },
            limit: { type: "number" },
            ageRange: { type: "string", enum: ["young", "adult", "senior"] },
          },
        },
      },
      {
        name: "vocea_transcribe",
        description: "Transcribe audio from a base64-encoded string to text (STT).",
        inputSchema: {
          type: "object",
          properties: {
            audio_base64: { type: "string", description: "Base64-encoded audio file (mp3, wav, ogg, webm, flac, max 10MB)" },
            mime_type: { type: "string", description: "MIME type, e.g. audio/mpeg", default: "audio/mpeg" },
            language: { type: "string", description: "BCP-47 language code, e.g. en-US (default: es-ES)" },
          },
          required: ["audio_base64"],
        },
      },
      {
        name: "vocea_get_credits",
        description: "Get the current credit balance for the authenticated user.",
        inputSchema: { type: "object", properties: {} },
      },
      {
        name: "vocea_get_audio",
        description: "Get details (including CDN URL) for a previously generated audio.",
        inputSchema: {
          type: "object",
          properties: { audio_id: { type: "string" } },
          required: ["audio_id"],
        },
      },
    ],
  }));