OpenAI TTS
Converts text to speech using OpenAI's TTS API with multiple voice options and audio formats. Can be used as an MCP server with Claude Desktop or as a standalone CLI tool.
1384 views2Local (stdio)
What it does
- Generate speech from text using OpenAI's TTS models
- Choose from multiple voice characters (alloy, nova, echo, etc.)
- Output audio in various formats (MP3, WAV, OPUS, AAC)
- Customize speech speed and voice parameters
- Run as CLI tool for direct text-to-speech conversion
- Integrate with Claude Desktop via MCP protocol
Best for
Adding voice narration to Claude Desktop conversationsDevelopers building voice-enabled applicationsContent creators needing high-quality text-to-speechCommand-line users wanting quick audio generation
Works with Claude DesktopNo installation required with npxMultiple voice characters available
