openai_create_transcription
Convert audio from a URL to text transcription with OpenAI Whisper. Choose output format and language as needed.
Instructions
Transcribe audio to text using OpenAI Whisper.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"api_key": "<api_key>",
"audio_url": "<audio_url>"
},
"name": "openai_create_transcription"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| model | No | Transcription model (default: whisper-1) | |
| prompt | No | ||
| api_key | Yes | ||
| filename | No | ||
| language | No | ISO-639-1 language code (optional) | |
| audio_url | Yes | URL of the audio file to transcribe | |
| temperature | No | ||
| response_format | No | json, text, srt, verbose_json, vtt (default: json) |