Upload your video. Captions, transcripts, and chapters — done.

WEBVTT

1
00:00:00.000 --> 00:00:02.560
The number one, I believe, sold for a million bucks.

2
00:00:10.560 --> 00:00:14.080
This is the National Stock and Bonds Show in Washington, D.C.

{
  "video_id": 454084,
  "model": "nvidia/parakeet-tdt-0.6b-v3",
  "language": "en",
  "words": [
    { "word": "The",    "start": 0.00, "end": 0.16, "confidence": 0.98 },
    { "word": "number", "start": 0.16, "end": 0.48, "confidence": 0.97 },
    { "word": "one,",   "start": 0.48, "end": 0.80, "confidence": 0.99 }
    // ... one entry per spoken word
  ]
}