v1

latestOpenAPI 3.1.02026-07-1381127211.1 KB

Video Emotion API

Get Video Multimodal Insights

Get complete multimodal analytics for a video including:

Video emotion analysis (face-by-face)
Audio emotion analysis (speaker-by-speaker)
Text sentiment analysis
Detected faces and speakers
Overall summaries

get/v2/videos/{video_id}/multimodal-analytics

Path parameters

video_idstring required

The unique ID of the video

Response

Successful Response

titlestring

statusstring

descriptionstring

created_atstring

media_typestring

video_idstring

audio_idstring

text_idstring

durationnumber

total_frames_countinteger

frame_ratenumber nullable

frame_heightnumber nullable

frame_widthnumber nullable

face_countinteger

speaker_countinteger

media_source_urlstring

annotated_video_urlstring

youtube_urlstring nullable

detected_facesobject[]

detected_speakersobject[]

Example response

{
  "title": "Customer Interview - Q4 2025",
  "status": "completed",
  "description": "Quarterly customer satisfaction interview",
  "created_at": "2025-12-01T14:30:00Z",
  "media_type": "video",
  "video_id": "01a5aceb-8411-4174-b80f-af6789dbd925",
  "audio_id": "1154940c-473f-46cb-a32d-923e6f23bedc",
  "text_id": "c74a3fe1-e8a3-4c7a-98c9-a496ee4a3fb8",
  "duration": 20.56,
  "total_frames_count": 87480,
  "frame_rate": 30,
  "frame_height": 1080,
  "frame_width": 1920,
  "face_count": 2,
  "speaker_count": 2,
  "media_source_url": "https://storage.googleapis.com/.../video.mp4",
  "annotated_video_url": "https://storage.googleapis.com/.../annotated.mp4",
  "detected_faces": [
    {
      "face_id": 1,
      "image": "https://storage.googleapis.com/.../faces/1.jpg",
      "name": "John Smith"
    },
    {
      "face_id": 2,
      "image": "https://storage.googleapis.com/.../faces/2.jpg",
      "name": ""
    }
  ],
  "detected_speakers": [
    {
      "name": "John Smith",
      "speaker_id": 1
    },
    {
      "name": "Interviewer",
      "speaker_id": 2
    }
  ],
  "emotion_analysis": {
    "overall": {
      "video": {
        "angry": 0.059,
        "happy": 0.175,
        "neutral": 0.408,
        "sad": 0.049
      },
      "audio": {
        "angry": 0.047,
        "happy": 0.185,
        "neutral": 0.638
      },
      "text": {
        "admiration": 0.015,
        "joy": 0.018,
        "neutral": 0.75
      }
    },
    "faces": {
      "John Smith": {
        "happy": 0.175,
        "neutral": 0.408,
        "sad": 0.049
      },
      "face_2": {
        "angry": 0.087,
        "happy": 0.184,
        "neutral": 0.314
      }
    },
    "speakers": {
      "Interviewer": {
        "audio": {
          "angry": 0.05,
          "happy": 0.18,
          "neutral": 0.65
        },
        "text": {
          "curiosity": 0.08,
          "neutral": 0.85
        }
      },
      "John Smith": {
        "audio": {
          "angry": 0.045,
          "happy": 0.19,
          "neutral": 0.625
        },
        "text": {
          "admiration": 0.02,
          "joy": 0.025,
          "neutral": 0.72
        }
      }
    }
  }
}