Audio Plugin
Transcribes audio files to text using a speech recognition API.
About
This plugin converts audio files (e.g., .wav, .mp3) into text transcripts using a speech recognition API. It is AIO-compliant, supporting both `multipart/form-data` and `base64` formats, and exposes the `identify_voice` method via the AIO `tools.call` protocol, returning JSON-RPC structured outputs. The API key is securely managed via a `.env` file, and the plugin is Docker-compatible with minimal dependencies, making it easy to deploy and integrate within an AIO environment.
Key Features
- Converts audio files to text transcripts
- Supports both multipart/form-data and base64 formats
- AIO-compliant MCP plugin
- API key managed securely via .env file
- Docker-compatible
- 1 GitHub stars
Use Cases
- Voice-to-text transcription within AIO environments
- Automated audio analysis and content extraction
- Integration with AIO endpoint registry