# voice-control

- Author: Mohamed Abdelaziz ‬‏
- Repository: Moeabdelaziz007/superpowers-marketplace
- Version: 20251222135548
- Stars: 0
- Forks: 0
- Last Updated: 2026-02-07
- Source: https://github.com/Moeabdelaziz007/superpowers-marketplace
- Web: https://mule.run/skillshub/@@Moeabdelaziz007/superpowers-marketplace~voice-control:20251222135548

---

# Skill: Voice Control (Gemini Live)

## Description
This skill enables the agent to interact via voice, simulating integration with the Gemini Live API. It handles audio input streams and generates speech output.

## Capabilities
1.  **Speech-to-Text (STT):** Transcribe user voice commands.
2.  **Text-to-Speech (TTS):** Generate natural-sounding voice responses.
3.  **Interrupt Handling:** Handle interruptions gracefully during playback.

## Usage Instructions
*   **Trigger:** Activated by specific voice commands or when the interface is in "Voice Mode".
*   **Protocol:** Stream audio chunks to the `process_audio_stream` tool.
*   **Persona:** Adopt a conversational tone. Sentences should be shorter and easier to listen to than to read.

## Tools (MCP)
*   `process_audio_stream(stream_id)`: Connects to a live audio feed.
*   `speak(text)`: Synthesizes text to speech.