Skip to content
Agentmart
Submit a tool

transcribe-audio

Transcribe an audio file (m4a, mp3, wav, ogg, webm) to text using OpenAI Whisper API.

Skill by irisworks

IndexedApache-2.0★ 13
Write a review

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/irisworks-transcribe-audio

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Transcribe an audio file (m4a, mp3, wav, ogg, webm) to text using OpenAI Whisper API. Use when a user shares a voice note or audio attachment.

Use cases: backend, productivity

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 and code. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found
Runs as
Shell scripts

Network hosts it talks to 2

  • api.openai.com · found in code
  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/transcribe-audio

What's inside

Skill name
transcribe-audio
Description
Transcribe an audio file (m4a, mp3, wav, ogg, webm) to text using OpenAI Whisper API. Use when a user shares a voice note or audio attachment.
License
Apache-2.0
Instructions
26 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Files (2)

  • SKILL.md
  • transcribe-audio.sh

SKILL.md (first lines)

# Skill: transcribe-audio

Transcribes audio files via OpenAI Whisper API. Supports m4a, mp3, mp4, wav, ogg, webm.
Max file size: 25MB. Returns plain text transcript.

## Usage

```bash
transcribe-audio /path/to/file.m4a
transcribe-audio /path/to/file.m4a --lang de   # hint language (ISO 639-1)
```

## Implementation

Script is at: {baseDir}/transcribe-audio.sh

Requires secret: `OPENAI-API-KEY` in Key Vault (fetched via get-secret).

## Notes

- Whisper auto-detects language if --lang not provided
- m4a files work natively — no conversion needed
- If file > 25MB, split with: `ffmpeg -i input.m4a -f segment -segment_time 300 -c copy out%03d.m4a`
- Transcript is printed to stdout — capture with: `text=$(transcribe-audio file.m4a)`

From irisworks/iris-core, Apache-2.0.

More from irisworks/iris-core

Signals

Stars
13
Forks
3
Open issues
7
Last commit (this folder)
Jul 24, 2026 (3 months ago)
Last release
Oct 14, 2026 (13 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
Apache-2.0
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from irisworks

Cite this page

transcribe-audio skill. Agent Mart. https://agentmart.dev/skills/irisworks-transcribe-audio (last updated 2026-10-24)