# Openai Whisper API

> Transcribe audio files via OpenAI Audio Transcriptions API (Whisper). Supports multiple formats with language detection and custom prompts.

- Skill: `yunseo-kim/openai-whisper-api` (Agent Skill, multi-file: 3 files)
- Install (CLI): `npx skillmds@latest add yunseo-kim/openai-whisper-api`
- Raw SKILL.md: https://api.skillmd.com/api/skills/yunseo-kim/openai-whisper-api/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Integrations & APIs
- License: Sustainable Use License 1.0
- Author: yunseo-kim (https://skillmd.com/u/yunseo-kim)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/yunseo-kim/openai-whisper-api

---


# OpenAI Whisper API (curl)

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

## Quick start

```bash
{skillDir}/scripts/transcribe.sh /path/to/audio.m4a
```

Defaults:

- Model: `whisper-1`
- Output: `<input>.txt`

## Useful flags

```bash
{skillDir}/scripts/transcribe.sh /path/to/audio.ogg --model whisper-1 --out /tmp/transcript.txt
{skillDir}/scripts/transcribe.sh /path/to/audio.m4a --language en
{skillDir}/scripts/transcribe.sh /path/to/audio.m4a --prompt "Speaker names: Peter, Daniel"
{skillDir}/scripts/transcribe.sh /path/to/audio.m4a --json --out /tmp/transcript.json
```

## API key

Set `OPENAI_API_KEY`, or configure it in `~/.the assistant/the assistant.json`:

```json5
{
  skills: {
    "openai-whisper-api": {
      apiKey: "OPENAI_KEY_HERE",
    },
  },
}
```