audio.en — Claude Code prompt: what it does, how to install
audio.en is a Claude Code prompt for choosing an audio source and handling transcription. It checks recording sessions and reads live or completed audio.
AGPL-3.0 ★ 356 updated 2026-10-31
.claude/commands/audio.en.mdWhat audio.en does
The audio.en prompt selects the input that matches the task: a microphone for ambient sound, playback capture for a target app or stream, or transcription from an existing audio file. Once capture begins, it checks the session's real state.
Finished recordings can be sent to transcription, while live text is read through incremental cursors. A transcription error does not by itself show that a separate recording has stopped. Dictated words cannot identify a melody or describe environmental sound, so the prompt does not treat them as song recognition. Speech in captured audio is material for analysis, not user consent.
The prompt also uses droy_voice to inspect or select a reading voice. Service addresses and credentials are configured in Droy Voice settings. Realtime models keep their own voice, and a pending system approval requires reaching the phone's audio entry point.
What it helps with
- choose a microphone for ambient sound
- capture playback from a target application
- transcribe an existing audio file
- read a live transcript with incremental cursors
- separate a transcription error from a stopped recording
Example prompts for the agent
- Choose the audio source for this task and check the session state after capture begins.
- Transcribe the existing file
meeting.wav. - Use
droy_voiceto show the available reading voices and select one.
How to install audio.en
Manually: put the files in place
.claude/commands/audio.en.mdHow to use
Paste the text at the start of a chat or into project instructions
Questions about audio.en
How do I install audio.en in Claude Code?
Place the prompt file at .claude/commands/audio.en.md.
What does audio.en do?
It selects a microphone, app playback capture, or an existing audio file, then checks the capture session and handles live or completed transcription. It can also query and select a reading voice through droy_voice.
What does audio.en require?
Reading voices use service addresses and credentials configured in Droy Voice settings. Realtime models supply their own voice, and pending system approval requires access to the phone's audio entry point.