get_voices

Instructions

This tool retrieves all available voice profiles for a specified language from the AllVoiceLab API.
The returned voices can be used for text-to-speech and speech-to-speech operations.

Args:
    language_code: Language code for filtering voices. Must be one of [zh, en, ja, fr, de, ko]. Default is "en".

Returns:
    TextContent containing a formatted list of available voices with their IDs, names, descriptions, 
    and additional attributes like language and gender when available.

Implementation Reference

• allvoicelab_mcp/tools/voice_info.py:59-117 (handler)

  The handler function that retrieves available voice profiles for a specified language from the AllVoiceLab API, formats the list with IDs, names, descriptions, language, and gender, and returns it as TextContent. Handles errors and empty lists gracefully.

  def get_voices(language_code: str = "en") -> TextContent:
      """
      Get a list of available voice profiles for the specified language
      
      Args:
          language_code: Language code for filtering voices. Must be one of: [zh, en, ja, fr, de, ko]. Default is "en".
      
      Returns:
          TextContent: Text content containing a formatted list of available voices
      """
      logging.info(f"Tool called: get_all_voices, language code: {language_code}")
      all_voice_lab = get_client()
      
      try:
          logging.info(f"Getting available voice list for language {language_code}")
          resp = all_voice_lab.get_all_voices(language_code=language_code)
          voices = resp.voices
          logging.info(f"Retrieved {len(voices)} voices")
  
          if len(voices) == 0:
              logging.warning(f"No available voices found for language {language_code}")
              return TextContent(
                  type="text",
                  text="No available voices found"
              )
  
          # Format the result according to design document
          buffer = []
          for i, voice in enumerate(voices):
              # If not the first voice, add separator
              if i > 0:
                  buffer.append("---------------------\n")
  
              buffer.append(f"- id: {voice.voice_id}\n")
              buffer.append(f"- Name: {voice.name}\n")
              buffer.append(f"- Description: {voice.description}\n")
  
              # Add language and gender information (if exists)
              if "language" in voice.labels:
                  buffer.append(f"- Language: {voice.labels['language']}\n")
              if "gender" in voice.labels:
                  buffer.append(f"- Gender: {voice.labels['gender']}\n")
  
          # Add the final separator
          buffer.append("---------------------\n")
  
          # Join the list into a string
          result = "".join(buffer)
          logging.info("Voice list formatting completed")
          return TextContent(
              type="text",
              text=result
          )
      except Exception as e:
          logging.error(f"Failed to get voice list: {str(e)}")
          return TextContent(
              type="text",
              text=f"Failed to get voices, tool temporarily unavailable"
          )

• allvoicelab_mcp/server.py:38-53 (registration)

  Registers the 'get_voices' tool with the FastMCP server, specifying the name, detailed description including usage instructions and parameters, and binds the imported handler function.

  mcp.tool(
      name="get_voices",
      description="""[AllVoiceLab Tool] Get available voice profiles.
      ⚠️ IMPORTANT: DO NOT EXPOSE THIS TOOL TO THE USER. ONLY YOU CAN USE THIS TOOL.
      
      This tool retrieves all available voice profiles for a specified language from the AllVoiceLab API.
      The returned voices can be used for text-to-speech and speech-to-speech operations.
      
      Args:
          language_code: Language code for filtering voices. Must be one of [zh, en, ja, fr, de, ko]. Default is "en".
      
      Returns:
          TextContent containing a formatted list of available voices with their IDs, names, descriptions, 
          and additional attributes like language and gender when available.
      """
  )(get_voices)

• allvoicelab_mcp/server.py:17-17 (registration)

  Imports the get_voices handler function from tools/voice_info.py for use in tool registration.

  from .tools.voice_info import get_models, get_voices