Our review
Transcribes an audio file via the OpenAI Whisper API using curl.
Strengths
- Supports many audio formats
- Customizable language and prompt options
- Output as plain text or JSON
- Simple and fast to run
Limitations
- Requires an OpenAI API key and internet connection
- Limited to the Whisper-1 model
- No real-time streaming
When you need a quick transcription of an audio file using OpenAI's Whisper.
For offline transcription or when you need to avoid API costs.
Security analysis
CautionThe skill runs a bash script that executes curl to interact with OpenAI's Audio API. While the operation is legitimate and no destructive commands are evident, it involves network transmission of user data and uses a powerful tool (bash), warranting caution.
- •Uses bash script and curl to send audio data to OpenAI API; user must ensure audio does not contain sensitive information.
- •Requires API key handling; misconfiguration could expose the key.
Examples
Transcribe this audio file using OpenAI Whisper: /path/to/meeting.m4aTranscribe this audio file with language set to French: /path/to/audio.ogg --language frTranscribe this audio file and output as JSON with a prompt for speaker names: /path/to/recording.mp3 --json --prompt "Speakers: John, Jane"name: openai-whisper-api description: Transcribe audio via OpenAI Audio Transcriptions API (Whisper). homepage: https://platform.openai.com/docs/guides/speech-to-text metadata: { "openclaw": { "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 ~/.openclaw/openclaw.json:
{
skills: {
"openai-whisper-api": {
apiKey: "OPENAI_KEY_HERE",
},
},
}
Prompt Engineering
Data & AI
Prompt engineering best practices and templates to maximize AI outputs.
Data Visualization
Data & AI
Generates data visualizations and charts tailored to your data.
RAG Architecture Setup
Data & AI
Setup guide for RAG (Retrieval-Augmented Generation) architectures.