# audio.en

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.

- prompt · `type=prompt` · Claude Code, ChatGPT · ★ 356 repo stars
- Author: moonoops
- License: AGPL-3.0 · policy=link-only · description only; the file stays with the author
- Source: https://github.com/moonoops/Droy/tree/HEAD/runtime/mobile/prompts/extensions/audio.en.md
- Updated: 2026-10-31
- Security check: automated, 2026-11-17 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/prompts/audioen

## What it 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.

## Install

### Claude Code (native platform)

**Manually: put the files in place**
- File: `.claude/commands/audio.en.md`

### ChatGPT

**How to use**
- Paste the text at the start of a chat or into project instructions

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/moonoops/Droy/tree/HEAD/runtime/mobile/prompts/extensions/audio.en.md

## When to use it
- 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
- Choose the audio source for this task and check the session state after capture begins.
- Transcribe the existing file `meeting.wav`.
- Use `droy_voice` to show the available reading voices and select one.

## Similar
- [audio-ducking](https://affpapa.org/en/nevibecode/skills/audio-ducking.md) — skill · 1300 installs
- [voice-audio-engineer](https://affpapa.org/en/nevibecode/skills/voice-audio-engineer.md) — skill · 388 installs
- [gemini-live-audio](https://affpapa.org/en/nevibecode/skills/gemini-live-audio.md) — skill · 137 installs
- [audio-router](https://affpapa.org/en/nevibecode/skills/audio-router.md) — skill · 1600 installs
- [audio-transcriber](https://affpapa.org/en/nevibecode/skills/audio-transcriber.md) — skill · 1400 installs
- [audio-transcription](https://affpapa.org/en/nevibecode/skills/audio-transcription.md) — skill · 1300 installs

From the same set: [moonoops/droy](https://affpapa.org/en/nevibecode/by/moonoops/droy.md) — 8 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
