openai-whisper-api
Transcribe audio via OpenAI Audio Transcriptions API (Whisper).
When & Why to Use This Skill
This Claude skill integrates the OpenAI Whisper API to provide high-accuracy audio-to-text transcription. It allows users to convert various audio formats (such as .m4a, .ogg, and .mp3) into structured text or JSON files. By leveraging the state-of-the-art Whisper-1 model, it supports multi-language transcription and custom prompts, making it an essential tool for transforming unstructured voice data into searchable, actionable text.
Use Cases
- Meeting Minutes & Documentation: Automatically transcribe recorded business meetings or Zoom calls to generate summaries, action items, and searchable archives.
- Content Creation & Repurposing: Convert podcast episodes, video voiceovers, or webinars into blog posts, social media snippets, or closed captions for SEO optimization.
- Research & Interviews: Transform journalistic, academic, or legal interviews into text for easier qualitative analysis, coding, and citation.
- Accessibility Compliance: Provide text-based alternatives for audio content to ensure digital accessibility for hearing-impaired users.
| name | openai-whisper-api |
|---|---|
| description | Transcribe audio via OpenAI Audio Transcriptions API (Whisper). |
| homepage | https://platform.openai.com/docs/guides/speech-to-text |
| metadata | {"clawdbot":{"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.
Quick start
{baseDir}/scripts/transcribe.sh /path/to/audio.m4a
Defaults:
- Model:
whisper-1 - Output:
<input>.txt
Useful flags
{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 ~/.clawdbot/clawdbot.json:
{
skills: {
"openai-whisper-api": {
apiKey: "OPENAI_KEY_HERE"
}
}
}