Transcribe
audio_transcriber_transcribeTranscribe audio files using an initialized speech-to-text backend, with optional language, task, and word-timestamp controls.
Instructions
Transcribe the audio file using the initialized backend.
Tool call template
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "audio_transcriber_transcribe"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| fp16 | No | ||
| task | No | transcribe | |
| verbose | No | ||
| language | No | ||
| temperature | No | ||
| initial_prompt | No | ||
| word_timestamps | No |