Voice Agent
A skill that enables bidirectional voice communication with users through the local Voice Agent API, supporting speech-to-text transcription and text-to-speech synthesis.
🚀 Voice Agent lets you communicate naturally using your voice. Simply speak, and the system transcribes your audio, processes your request, and responds with synthesized speech—creating a seamless hands-free conversation experience.
💡 Perfect for accessibility, multitasking, or situations where typing isn't practical. Use it for voice commands, interactive conversations, customer support, or any scenario where natural speech interaction enhances usability.
✨ Audio-first design means responses come back as voice files, keeping interactions fluid and natural without unnecessary text clutter.
Requirements
Local Voice Agent API service for speech-to-text and text-to-speech operations