voice

Privacy-aware TTS applies mic and speaker mute rules to protect sensitive conversations during spoken audio output. It coordinates mute controls to prevent unintended audio capture while converting chat replies into speech.

To convert chat replies into spoken audio, you use the text-to-speech endpoint to generate speech output. This enables hands-free communication by automatically reading replies aloud while applying privacy mute controls.

Yes, you can trigger speech output automatically when sensing events occur. The skill provides operational guidance for reacting to sensing events and ensures spoken feedback occurs at the correct moment during privacy-sensitive interactions.

Yes, this TTS skill supports optional parallel tool calls while generating speech output. It converts chat replies into spoken audio via TTS and allows simultaneous tool execution during hands-free communication scenarios.

The ambient guard limitation involves ensuring speech output only occurs at appropriate moments to maintain privacy. It enforces environmental checks before generating spoken audio, preventing TTS output during unsuitable ambient conditions.