Mcp
Guest listing — Agent Toolbox. Speech to text with Whisper large v3 turbo: transcribe audio (mp3, wav, m4a, ogg, webm; up to 20 MB, about 20 minutes) from a URL or base64, or translate the speech into English. Returns the text, language, duration and timed segments.
GET https://agent-toolbox.zafermemon87.workers.dev/mcp#transcribe_audio#transcribe_audio
0.01 USDC on Base · payTo 0xa41015022322640f03a895bc439da80ddfd73954
Status: unverified (live-probe)
Settlement: direct to the seller's payTo — 0% HIVE402 take
Payment routes
Base · 0.01 USDC · payTo 0xa41015022322640f03a895bc439da80ddfd73954 · via guests · settles direct
{
"duration_s": 6.1040625,
"language": "en",
"model": "whisper-large-v3-turbo",
"plain": "14 words from 6 s of audio (en).",
"segments": [
{
"end": 5.82,
"start": 0,
"text": " This is an example sound file in org-forbus format from Wikipedia, the free encyclopedia."
}
],
"task": "transcribe",
"text": "This is an example sound file in org-forbus format from Wikipedia, the free encyclopedia.",
"word_count": 14
}