The Mobvoi TTS MCP Server enables interaction with Mobvoi's Text-to-Speech (TTS) and Voice Clone APIs, allowing you to:
Voice Cloning: Clone voices from URL or local audio files to get a speaker ID
Speech Synthesis: Generate speech from text using specified or default speakers, with customizable parameters (speed, volume, pitch, sampling rate)
Voice Broadcasting: Play audio files in WAV or MP3 format
Asynchronous Operations: Perform voice cloning and TTS tasks asynchronously
Cost Management: Includes warnings about potential API call costs