$npx -y skills add SafeAI-Lab-X/ClawKeeper --skill openai-whisper-apiTranscribe audio via OpenAI Audio Transcriptions API (Whisper).
| 1 | # OpenAI Whisper API (curl) |
| 2 | |
| 3 | Transcribe an audio file via OpenAI’s `/v1/audio/transcriptions` endpoint. |
| 4 | |
| 5 | ## Quick start |
| 6 | |
| 7 | ```bash |
| 8 | {baseDir}/scripts/transcribe.sh /path/to/audio.m4a |
| 9 | ``` |
| 10 | |
| 11 | Defaults: |
| 12 | |
| 13 | - Model: `whisper-1` |
| 14 | - Output: `<input>.txt` |
| 15 | |
| 16 | ## Useful flags |
| 17 | |
| 18 | ```bash |
| 19 | {baseDir}/scripts/transcribe.sh /path/to/audio.ogg --model whisper-1 --out /tmp/transcript.txt |
| 20 | {baseDir}/scripts/transcribe.sh /path/to/audio.m4a --language en |
| 21 | {baseDir}/scripts/transcribe.sh /path/to/audio.m4a --prompt "Speaker names: Peter, Daniel" |
| 22 | {baseDir}/scripts/transcribe.sh /path/to/audio.m4a --json --out /tmp/transcript.json |
| 23 | ``` |
| 24 | |
| 25 | ## API key |
| 26 | |
| 27 | Set `OPENAI_API_KEY`, or configure it in `~/.openclaw/openclaw.json`: |
| 28 | |
| 29 | ```json5 |
| 30 | { |
| 31 | skills: { |
| 32 | "openai-whisper-api": { |
| 33 | apiKey: "OPENAI_KEY_HERE", |
| 34 | }, |
| 35 | }, |
| 36 | } |
| 37 | ``` |