Openai Whisper Api

A straightforward wrapper around OpenAI's Whisper transcription API using curl. You point it at an audio file (m4a, ogg, whatever Whisper supports), and it spits out a text transcript. Supports the usual options like language hints, custom prompts for better accuracy with speaker names, and JSON output if you need structured data. The nice touch is OPENAI_BASE_URL support, so you can swap in a local gateway or proxy without changing your workflow. It's the kind of tool you drop into a script when you need quick transcription without installing Python dependencies or dealing with the Whisper model locally. Does one thing, does it simply.

skills.sh installs: 2.7K
GitHub stars: 382.8K
last updated: Jul 14, 2026

View on GitHub

Install

$ npx -y skills add steipete/clawdis --skill openai-whisper-api --agent claude-code

Installs into .claude/skills of the current project.

Files

OpenAI transcriptions API

Transcribe audio through /v1/audio/transcriptions. Set OPENAI_BASE_URL for an OpenAI-compatible proxy or local gateway.

Quick start

{baseDir}/scripts/transcribe.sh /path/to/audio.m4a

Defaults:

Model: gpt-4o-transcribe
Output: <input>.txt

Useful flags

{baseDir}/scripts/transcribe.sh /path/to/audio.ogg --model gpt-4o-transcribe --out /tmp/transcript.txt
{baseDir}/scripts/transcribe.sh /path/to/audio.ogg --model gpt-4o-mini-transcribe
{baseDir}/scripts/transcribe.sh /path/to/audio.ogg --model gpt-4o-transcribe-diarize --json
{baseDir}/scripts/transcribe.sh /path/to/audio.ogg --model whisper-1
{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

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 chunking_strategy=auto and rejects --prompt.