audio-transcriber
SKILL.md
Audio Transcriber
Transcribe audio/video files to text using OpenAI Whisper.
Usage
node dist/index.js [options]
Troubleshooting
| Error | Cause | Fix |
|---|---|---|
ffmpeg: command not found |
FFmpeg not installed | Install: brew install ffmpeg (macOS) or apt install ffmpeg (Linux) |
Cannot find module 'openai' |
OpenAI SDK not installed | Run npm install openai |
OPENAI_API_KEY is not set |
API key missing | Set export OPENAI_API_KEY=sk-... in your shell |
Error: 413 Request Entity Too Large |
Audio file exceeds 25MB limit | Split file: ffmpeg -i input.mp3 -ss 0 -t 600 part1.mp3 |
Unsupported audio format |
File format not recognized | Convert to mp3/wav: ffmpeg -i input.ogg output.mp3 |
Knowledge Protocol
- This skill adheres to the
knowledge/orchestration/knowledge-protocol.md. It automatically integrates Public, Confidential (Company/Client), and Personal knowledge tiers, prioritizing the most specific secrets while ensuring no leaks to public outputs.
Weekly Installs
17
Repository
famaoai-creator…i-skillsGitHub Stars
1
First Seen
Feb 13, 2026
Security Audits
Installed on
cursor17
opencode16
gemini-cli16
replit16
claude-code16
github-copilot16