Agent skill · software engineering · steipete
openai-whisper-api
OpenAI Audio Transcriptions API via curl; gpt-4o-transcribe, mini, diarize, or whisper-1.
Why this skill is useful
Adds executable scripts for audio transcription using OpenAI's Whisper API that aren't in public docs.
What it needs
Requires curl, node installed locally. Requires openai account access. About 1k tokens when loaded. Last updated 2026-08-07. 385,400 stars on the source repository.
What this skill does
OpenAI transcriptions API Transcribe audio through /v1/audio/transcriptions. Set OPENAIBASEURL for an OpenAI-compatible proxy or local gateway. Quick start Defaults: Model: gpt-4o-transcribe Output: <input>.txt Useful flags Notes: Supported upload formats include mp3, mp4, mpeg, mpga, m4a, wav, webm. 25 MB upload limit on the hosted API. Use diarize for speaker labels; script sends chunkingstrategy=auto and rejects --prompt. API key Set OPENAIAPIKEY, or configure it in the active OpenClaw config file ($OPENCLAWCONFIGPATH, default ~/.openclaw/openclaw.json). Optionally set OPENAIBASEURL:
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills steipete/openai-whisper-api