Openai Whisper
Transcribes audio meetings and calls using OpenAI's Whisper model, providing searchable text for improved collaboration.
Install on your platform
We auto-selected Claude Code based on this skill’s supported platforms.
Run in terminal (recommended)
claude mcp add cowork-os-openai-whisper npx -- -y @trustedskills/cowork-os-openai-whisper
Or manually add to ~/.claude/settings.json
{
"mcpServers": {
"cowork-os-openai-whisper": {
"command": "npx",
"args": [
"-y",
"@trustedskills/cowork-os-openai-whisper"
]
}
}
}Requires Claude Code (claude CLI). Run claude --version to verify your install.
About This Skill
What it does
This skill utilizes OpenAI's Whisper model to transcribe audio into text. It can process various audio formats and languages, providing a convenient way to convert spoken words into written content. The transcription output is intended for downstream tasks such as summarization or analysis.
When to use it
- Transcribing meeting recordings for documentation purposes.
- Converting voice notes into editable text documents.
- Generating captions for videos or podcasts.
- Creating transcripts from audio files in different languages.
Key capabilities
- Audio transcription using OpenAI Whisper
- Support for various audio formats
- Transcription across multiple languages
Example prompts
- "Transcribe this audio file: [audio_file]"
- "What was said in this recording? [audio_file]"
- “Can you create a text transcript of the attached audio?”
Tips & gotchas
The accuracy of transcription depends on audio quality and clarity. Ensure the input audio is as clean as possible for optimal results.
Tags
TrustedSkills Verification
Unlike other registries that point to live repositories, TrustedSkills pins every skill to a verified commit hash. This protects you from malicious updates — what you install today is exactly what was reviewed and verified.
Security Audits
| Gen Agent Trust Hub | Pass |
| Socket | Pass |
| Snyk | Pass |
🌐 Community
Passed automated security scans.