listen-once

To capture a single voice input and receive a text transcription, the Skill invokes the voice converse tool once to listen for your speech, skips text-to-speech output, and returns the transcription as plain text. This provides a one-shot voice capture with no spoken feedback.

Yes, single-shot speech-to-text is designed for quiet environments by disabling text-to-speech playback entirely. The Skill captures your spoken input once and returns the transcript strictly as text, ensuring no audible response is generated.

The best way to accept one voice command and get a plain-text answer is using a single-shot voice capture mechanism. It displays a listening prompt, records your speech, transcribes it, and returns the text output without initiating a continuous conversation.

No, single-shot voice capture does not support follow-up questions or continuous conversation. It calls the converse tool exactly once to listen for a single response and immediately returns the text transcription, terminating the interaction without spoken feedback.

Your voice transcription returns as text instead of spoken audio because the Skill explicitly skips text-to-speech processing. It captures a single voice input and routes the speech-to-text transcription directly as a text-only response for quick, silent reading.