Overview
Use when an agent must turn audio into text (meetings, calls, voice notes). Input: POST a file (multipart 'file', raw body, JSON audioBase64) or url; mp3, wav, m4a, ogg, webm, flac, max 25 MB / 10 min. Output: text, language, timestamped segments, word count, duration; summary=true adds summary, key points, action items. $0.006 per started minute (+$0.004 summary), quoted before payment. Not stored. Example: POST {"url":"https://.../call.mp3"}
Protocol
x402
Price
$0.0060
Payment Asset
USD Coin
Payment Network
eip155:8453
Category
uncategorized
Provider
Speech-to-Text
Indexed
2026-11-06 06:02:21
Health
Status
unknown
Latency (p50)
—
Uptime (30d)
—
Reliability Score
—
Last Checked
Never
Last Healthy
Never
Consecutive Failures
0
Input Schema
{
"method": "GET",
"queryParams": {
"language": "auto",
"summary": "false",
"url": "https://www2.cs.uic.edu/~i101/SoundFiles/gettysburg10.wav"
},
"type": "http"
}
Output Schema
{
"example": {
"billedMinutes": 1,
"bytes": 587110,
"chars": 121,
"durationSeconds": 6.66,
"format": "wav",
"language": "en",
"languageProbability": 1,
"model": "@cf/openai/whisper-large-v3-turbo",
"notes": [
"Transcribed by Whisper large-v3-turbo on Cloudflare Workers AI; check names and figures against the audio. Audio is processed in memory and never stored."
],
"price": "$0.01",
"segments": [
{
"end": 3.96,
"start": 0,
"text": "Good morning, everyone. The quarterly review is moved to Thursday at 2 p.m."
}
],
"speechSeconds": 6.66,
"summary": {
"actionItems": [
"Sarah to send the updated budget by Friday"
],
"keyPoints": [
"Quarterly review moved to Thursday at 2 p.m."
],
"model": "@cf/google/gemma-4-26b-a4b-it",
"summary": "The quarterly review has been rescheduled to Thursday at 2 p.m. Sarah is responsible for sending the updated budget by Friday."
},
"text": "Good morning, everyone. The quarterly review is moved to Thursday at 2 p.m. Sarah will send the updated budget by Friday.",
"warnings": [],
"wordCount": 21
},
"type": "json"
}