transcribe-audio

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/drew-council-transcribe-audio

About

Use cases: documents

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools

No tools found

Secrets

None asked for

Install scripts

None found

Runs as

Node.js package

What's inside

Skill name

transcribe-audio

Description

Manually transcribe a spoken-word audio file with OpenAI gpt-transcribe. This skill must only be used when explicitly invoked by the user.

License

MIT

Compatibility

Requires Bun, ffprobe, network access, and openai.apiKey in ~/.pi/secrets/personal.json.

Instructions

19 lines in SKILL.md · view on GitHub

# Transcribe Audio

Run the script by its home-relative path so it works from any current directory:

```bash
{{skillDir}}/scripts/transcribe-audio.ts -- <audio-path>
```

Add transcription context when the user provides expected proper nouns, acronyms, technical terms, a topic, or preferred spelling:

```bash
{{skillDir}}/scripts/transcribe-audio.ts --prompt '<context>' -- <audio-path>
```

The script accepts mp3, mp4, mpeg, mpga, m4a, wav, and webm files up to 25 MB. It validates the media with `ffprobe`, calls OpenAI `gpt-transcribe`, and saves the complete transcript under `~/.pi/agent/transcriptions/`.

After it succeeds, read the returned `outputPath`. Do not expose the API key or the contents of the secrets file.

Signals

Stars

0

Forks

0

Open issues

0

Last commit (this folder)

Oct 16, 2026 (13 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License

MIT

Repository

github.com/drew-council/pi-config

First seen

Oct 24, 2026

Last checked

Oct 24, 2026

Source

GitHubgithub-graphql