Video

Video Transcription

Convert speech to text with timestamps for video content

385K runs

Note: This playground provides simulated output to showcase functionality. No input data is processed or stored on our servers. Use this demo to explore the feature extractor's capabilities before integrating it into your application.

Input

File URL string

Enter a URL to a video file

Upload video

Drag and drop a video file here, or click to browse

Select File

# model string

The transcription model to use. Default: whisper

# language string

Language of the audio. Default: auto

# min_confidence number

Minimum confidence threshold for transcription. Default: 0.6

# include_speakers boolean

Whether to include speaker diarization. Default: true

Output

{
  "transcript": [
    {
      "start": 0.5,
      "end": 4.2,
      "text": "Welcome to our product demonstration.",
      "speaker": "speaker_1"
    },
    {
      "start": 5.1,
      "end": 9.8,
      "text": "Today we'll show you how this technology works.",
      "speaker": "speaker_1"
    },
    {
      "start": 10.3,
      "end": 15.9,
      "text": "Let me explain the key features.",
      "speaker": "speaker_2"
    }
  ],
  "speakers": 2,
  "language": "en",
  "confidence": 0.94
}