Transcribe audio
audio_transcribeTranscribes an audio file at a public https URL on EdgeCloud and returns the text. Charges credits per audio minute, only on success; price it with quote. Needs sign-in (auth_challenge then auth_verify).
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": {
"audio_url": "<audio_url>",
"minutes": "<minutes>"
},
"name": "audio_transcribe"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| minutes | Yes | Audio length in whole minutes for pricing, 1-30 | |
| quote_id | No | The quote_id returned by quote (valid 5 minutes, single use). Use instead of max_price_credits | |
| audio_url | Yes | Public https link to the audio file | |
| max_price_credits | No | The most you'll pay for this call, in Wave credits. Needed unless you pass quote_id; the call fails if the price is higher |