repositories
loading repo index
repositories
loading repo index
repository
loading code, commits, and activity
public Clawd ADK gateway launch mirror
stars
latest
clone command
git clone gitlawb://did:key:z6Mkq5mY...iFZ5/my-project-publ...git clone gitlawb://did:key:z6Mkq5mY.../my-project-publ...2fa351d6docs: add automaton and perps launch sources16d ago| #1 | --- |
| #2 | name: openai-whisper-api |
| #3 | description: Transcribe audio via OpenAI Audio Transcriptions API (Whisper). |
| #4 | homepage: https://platform.openai.com/docs/guides/speech-to-text |
| #5 | metadata: {"clawdbot":{"emoji":"☁️","requires":{"bins":["curl"],"env":["OPENAI_API_KEY"]},"primaryEnv":"OPENAI_API_KEY"}} |
| #6 | --- |
| #7 | |
| #8 | # OpenAI Whisper API (curl) |
| #9 | |
| #10 | Transcribe an audio file via OpenAI’s `/v1/audio/transcriptions` endpoint. |
| #11 | |
| #12 | ## Quick start |
| #13 | |
| #14 | ```bash |
| #15 | {baseDir}/scripts/transcribe.sh /path/to/audio.m4a |
| #16 | ``` |
| #17 | |
| #18 | Defaults: |
| #19 | - Model: `whisper-1` |
| #20 | - Output: `<input>.txt` |
| #21 | |
| #22 | ## Useful flags |
| #23 | |
| #24 | ```bash |
| #25 | {baseDir}/scripts/transcribe.sh /path/to/audio.ogg --model whisper-1 --out /tmp/transcript.txt |
| #26 | {baseDir}/scripts/transcribe.sh /path/to/audio.m4a --language en |
| #27 | {baseDir}/scripts/transcribe.sh /path/to/audio.m4a --prompt "Speaker names: Peter, Daniel" |
| #28 | {baseDir}/scripts/transcribe.sh /path/to/audio.m4a --json --out /tmp/transcript.json |
| #29 | ``` |
| #30 | |
| #31 | ## API key |
| #32 | |
| #33 | Set `OPENAI_API_KEY`, or configure it in `~/.clawdbot/clawdbot.json`: |
| #34 | |
| #35 | ```json5 |
| #36 | { |
| #37 | skills: { |
| #38 | "openai-whisper-api": { |
| #39 | apiKey: "OPENAI_KEY_HERE" |
| #40 | } |
| #41 | } |
| #42 | } |
| #43 | ``` |
| #44 |