Labsco
firecrawl logo

openai-whisper-api

✓ Official★ 3

by firecrawl · part of firecrawl/openclaw

Transcribe audio via OpenAI Audio Transcriptions API (Whisper).

🔥🔥🔥✓ VerifiedAccount requiredNeeds API keys
#scraping#voice#git
🧰 Not standalone. This skill ships with firecrawl/openclaw and only works together with that tool — install the tool first, then add this skill.

Transcribe audio via OpenAI Audio Transcriptions API (Whisper).

Inspect the full instructions your agent will receiveExpand

This is the exact playbook injected into your agent when the skill activates — shown here so you can audit it before installing. You don't need to read it to use the skill.

name: openai-whisper-api description: Transcribe audio via OpenAI Audio Transcriptions API (Whisper). homepage: https://platform.openai.com/docs/guides/speech-to-text metadata: { "openclaw": { "emoji": "☁️", "requires": { "bins": ["curl"], "env": ["OPENAI_API_KEY"] }, "primaryEnv": "OPENAI_API_KEY", }, }

OpenAI Whisper API (curl)

Transcribe an audio file via OpenAI’s /v1/audio/transcriptions endpoint.

Useful flags

Copy & paste — that's it
{baseDir}/scripts/transcribe.sh /path/to/audio.ogg --model whisper-1 --out /tmp/transcript.txt
{baseDir}/scripts/transcribe.sh /path/to/audio.m4a --language en
{baseDir}/scripts/transcribe.sh /path/to/audio.m4a --prompt "Speaker names: Peter, Daniel"
{baseDir}/scripts/transcribe.sh /path/to/audio.m4a --json --out /tmp/transcript.json

API key

Set OPENAI_API_KEY, or configure it in ~/.openclaw/openclaw.json:

Copy & paste — that's it
{
  skills: {
    "openai-whisper-api": {
      apiKey: "OPENAI_KEY_HERE",
    },
  },
}