Video

Speaker Diarization

Identify and separate different speakers in audio

320K 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 diarization model to use. Default: pyannote-v2

# min_speakers integer

Minimum number of speakers to detect. Default: 1

# max_speakers integer

Maximum number of speakers to detect. Default: 10

# min_segment_duration number

Minimum duration for speaker segments in seconds. Default: 0.5

Output

{
  "speakers": [
    {
      "id": "speaker_1",
      "segments": [
        {
          "start": 0,
          "end": 12.5
        },
        {
          "start": 35.2,
          "end": 48.1
        }
      ],
      "total_time": 25.4
    },
    {
      "id": "speaker_2",
      "segments": [
        {
          "start": 12.8,
          "end": 34.9
        },
        {
          "start": 48.5,
          "end": 62.3
        }
      ],
      "total_time": 35.9
    }
  ],
  "total_speakers": 2,
  "speaker_characteristics": [
    {
      "id": "speaker_1",
      "gender": "female",
      "estimated_age": "adult"
    },
    {
      "id": "speaker_2",
      "gender": "male",
      "estimated_age": "adult"
    }
  ]
}