Speech-to-text (Whisper large v3 turbo)
ai_transcribeUse when an agent is handed audio and needs text it can work with: Whisper large v3 turbo - pass an https URL (mp3, wav, flac, m4a, ogg, up to 10 MB) or base64 audio in a POST. Returns the text, the detected language with its probability, the duration, and timed segments; add words=true for word-level timestamps. Around 100 languages. You are only charged if the transcript is delivered. No API key, no account. $0.02 per call, paid over x402 (USDC).
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": "ai_transcribe"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | No | https URL of the audio file, up to 10 MB. | |
| audio | No | Alternative to url: the audio as base64 (POST only). | |
| words | No | Include word-level timestamps. Default false. | |
| language | No | Optional ISO code to skip detection, e.g. es. |