Blabber
Converts text into spoken audio using OpenAI's Text-to-Speech API.
About
Blabber gives your LLMs a voice by serving as an MCP server that leverages OpenAI's Text-to-Speech API. It allows you to convert text input into high-quality spoken audio, offering options for voice and model selection, audio format, file saving, and optional playback via configurable system commands. Configure it within your MCP client's settings to utilize this powerful text-to-speech capability.
Key Features
- Voice selection (alloy, echo, fable, onyx, nova, shimmer)
- Text-to-Speech conversion
- File saving and optional playback
- Audio format options (mp3, opus, aac, flac)
- 1 GitHub stars
- Model selection (tts-1, tts-1-hd)
Use Cases
- Adding voice output to LLM applications
- Generating speech for interactive experiences
- Creating audio versions of text-based content