Imentiv AI Video Emotion API API
The Video Emotion Analysis API by Imentiv analyzes the emotional states of individuals in a video. It performs multi-modal emotion detection using facial expressions, audio, and text transcript, and has the following features:- Overall emotion summary- Frame-by-frame emotion data- Per-face emotional analysis- Valence-arousal-intensity data- Audio and transcript emotion data- Personality analysis- Video Highlights- Optional psychological insights
Imentiv AI Video Emotion API API is one of 6 APIs that Imentiv AI publishes on the APIs.io network, described by a machine-readable OpenAPI specification.
Tagged areas include Video Emotion API. The published artifact set on APIs.io includes an OpenAPI specification and API documentation.
This API exposes 30 operations across 24 paths, and defines 54 schemas. It is described by OpenAPI 3.1.0, at version 1.0.0.
Requests are made against the base URL https://api.imentiv.ai.
30 operations
24 paths
54 schemas
2 DELETE14 GET5 POST9 PUT
Metadata
The identity and technical contract details declared by the specification.
Authentication & Security 1
Imentiv AI Video Emotion API API declares
1 security scheme
for authenticating requests.
An API key is passed in the header as X-API-Key (APIKeyHeader).
Paths & Operations 30
Across 24 paths, the API surfaces 30 operations — 2 DELETE, 14 GET, 5 POST, 9 PUT. Each is listed below with its method, path, parameters, and response codes.
Video Emotion API 30
The Video Emotion Analysis API by Imentiv analyzes the emotional states of individuals in a video. It performs multi-modal emotion detection using facial expressions, audio, and t…
POST
/v2/videos
Upload Video
GET
/v1/videos
List Videos
GET
/v1/videos/{video_id}
Get Video Emotion Insights
DELETE
/v1/videos/{video_id}
Delete Video
PUT
/v1/videos/{video_id}
Reprocess Video
GET
/v2/videos/{video_id}/multimodal-analytics
Get Video Multimodal Insights
GET
/v2/videos/{video_id}/emotions/average
Get Average Emotions
GET
/v2/videos/{video_id}/annotated_video
Get Annotated Video
GET
/v1/videos/{video_id}/valence_arousal
Get Valence Arousal
GET
/v1/videos/{video_id}/frames
Get Multiple Frame
GET
/v1/videos/{video_id}/frames/{frame_id}
Get Single Frame
GET
/v1/videos/{video_id}/frames/{frame_id}/dominant_emotion
Retrieve Domination Emotion For A Specific Frame
GET
/v1/videos/{video_id}/frames/{frame_id}/valence_arousal
Retrieve Emotion Intensity
PUT
/v1/videos/{video_id}/frames/{frame_id}/faces/{face_id}/emotions
Update Emotion Per Frame
PUT
/v1/videos/{video_id}/frames/{frame_id}/faces/{face_id}/note
Edit Face Note
PUT
/v1/videos/{video_id}/frames/faces
Update Multiple Faces
PUT
/v1/videos/{video_id}/faces
Merge Face
DELETE
/v1/videos/{video_id}/faces
Delete Faces
PUT
/v1/videos/{video_id}/faces/names
Update Faces Names
POST
/v1/videos/highlights
Process Highlight
GET
/v1/videos/{video_id}/highlights
Fetch Highlight Video
PUT
/v1/videos/{video_id}/highlights
Update Highlight Video
GET
/v1/videos/{video_id}/highlight_video
Download Highlight Video
PUT
/v1/videos/{video_id}/metadata
Edit Title Or Description By Id
POST
/v1/videos/{video_id}/report
Generate Video Emotion Analysis Report
GET
/v1/videos/{video_id}/report
Download Video Emotion Analysis Report
PUT
/v2/videos/{video_id}/speaker-face-match
Update Speaker Face Match
POST
/v2/videos/{video_id}/speaker-face-match
Trigger Speaker Face Match
POST
/v2/videos/{video_id}/personality/analyze
Trigger Personality Analysis
GET
/v2/videos/{video_id}/faces/{face_id}/personality-analysis
Get Personality Analysis
Schemas 54
The contract defines 54 schemas that model the data the API accepts and returns. The most detailed are FullVideoAnalyticsResponse (21 properties), VideoResponse (18 properties), Body_update_emotion_per_frame_v1_videos__video_id__frames__frame_id__faces__face_id__emotions_put (8 properties), VideoEmotionResponseV2 (8 properties). Each schema is shown below with its type and property counts.
ValidationError
object
3 properties
3 required
MultiFaceResponse
object
Response model after updating multiple faces. Attributes: message (str): Operation status or result. updatedframes (List): List of frames with updated faces.
2 properties
2 required
PaginatedResponse
object
Model for paginated audio emotion responses. Attributes: documents (List[AudioEmotionResponse]): List of audio responses. count (int): Total count of documents.
2 properties
2 required
MultipleFramesResponse
object
Model for returning the MultipleFrame Responses
1 property
1 required
FullVideoAnalyticsResponse
object
Complete multimodal analytics response for video content.
21 properties
1 required
HighlightResponse
object
Model for highlight video response. Attributes: message (str): Status or success message. highlighturl (str): URL to the generated highlight video.
2 properties
EmotionAnalysis
object
Hierarchical emotion analysis structure.
3 properties
1 required
VideoDeleteResponse
object
Response after deleting a video entry. Inherits: ResponseStatus: Generic response with status and message.
2 properties
2 required
VideoEmotionResponseV2
object
V2 response model for video emotion detection with URL source tracking. Supports: - YouTube URLs - Cloud storage URLs (Dropbox, direct URLs, etc.) - Social Med…
8 properties
7 required
PersonalitySegmentMetrics
object
Segment-level personality analysis with segment interval and list of segments. Attributes: segmentintervalmillis (int): Interval duration in milliseconds segme…
2 properties
2 required
ReprocessVideoResponse
object
Response returned after requesting reprocessing of a video. Inherits from: GenerateCSVResponse
3 properties
3 required
BoundingBox
object
PersonalityTriggerResponse
object
Response model returned after triggering personality processing for a specific face (and optionally a speaker) within a video. Attributes: videoid (str): Uniqu…
6 properties
5 required
AnnotatedVideoResponse
object
Response for annotated video generation status. Attributes: videoid (str): ID of the video. message (str): Status message. status (str): Current status of anno…
3 properties
3 required
AutoSpeakerFaceMatchTriggerResponse
object
Response model for triggering the automatic speaker-face match worker. Attributes: videoid (str): Unique identifier of the video. audioid (str): Unique identif…
4 properties
4 required
Body_merge_face_v1_videos__video_id__faces_put
object
2 properties
2 required
ListOfFaces
object
Model representing a collection of faces. Attributes: faces (List[Faces]): List of detected or named faces.
1 property
1 required
PersonalityOceanMetrics
object
OCEAN personality trait metrics (Big Five personality traits). Attributes: agreeableness (float): Agreeableness level (0-1 range) conscientiousness (float): Co…
5 properties
5 required
VideoResponse
object
Model representing detailed video metadata and analysis. Attributes: title (Optional[str]): Title of the video. description (str): Description of the video. id…
18 properties
2 required
Body_delete_faces_v1_videos__video_id__faces_delete
object
1 property
1 required
Body_upload_video_v2_videos_post
object
8 properties
1 required
VideoEditResponse
object
Response model after editing a video. Inherits: ImageEditResponse: Includes status and edit metadata.
2 properties
DeleteFacesResponse
object
Response model after deleting one or more faces. Attributes: id (str): Video or frame ID the faces belonged to. message (str): Confirmation or error message.
2 properties
2 required
SpeakerEmotions
object
Speaker-specific emotions across audio and text modalities.
2 properties
Body_reprocess_video_v1_videos__video_id__put
object
2 properties
NameUpdateResponse
object
Model for updating the name associated with a face. Attributes: faceid (int): Identifier of the face being updated. name (str): New name to assign to the face.
2 properties
2 required
SignedDownloadUrlResponse
object
Response containing a signed URL for downloading annotated video. Attributes: videoid (str): ID of the video. downloadurl (str): Signed URL for downloading the…
6 properties
5 required
Body_process_highlight_v1_videos_highlights_post
object
1 property
1 required
Body_edit_face_note_v1_videos__video_id__frames__frame_id__faces__face_id__note_put
object
1 property
1 required
Faces
object
Model representing a detected face. Attributes: image (str): Image data (base64 or URL) of the face. name (Optional[str]): Optional name of the person. faceid…
3 properties
2 required
Body_update_multiple_faces_v1_videos__video_id__frames_faces_put
object
3 properties
3 required
HighlightGenerateResponse
object
Model for highlight video generation trigger response. Attributes: videoid (str): The video ID for which highlights are being generated. message (str): Status…
3 properties
3 required
FrameEmotionResponseData
object
Model for dominant emotion data of a frame. Attributes: frameid (str): Identifier for the video frame. faceid (Optional[int]): Face ID detected in the frame. d…
4 properties
1 required
UpdateEmotionResponse
object
Model representing updated emotion values for a face. Attributes: frameid (str): Frame identifier. faceid (int): ID of the face. emotions (Dict[str, float]): D…
3 properties
3 required
FrameNoteResponse
object
Model for response after adding a note to a frame. Attributes: id (str): Frame ID or reference. status (str): Status of the note operation.
2 properties
2 required
SpeakerFaceMatchRequest
object
Request model for mapping a detected face to a speaker with an optional name. Attributes: speakerid (int): Unique identifier for the speaker from audio analysi…
3 properties
3 required
Body_update_emotion_per_frame_v1_videos__video_id__frames__frame_id__faces__face_id__emotions_put
object
8 properties
SegmentResponse
object
Model for a video segment time range. Attributes: startmillis (float): Start time in milliseconds. endmillis (float): End time in milliseconds.
2 properties
2 required
Body_generate_video_emotion_analysis_report_v1_videos__video_id__report_post
object
1 property
PersonalityAnalysisStatus
object
Status detail for personality analysis processing. Attributes: status (str): One of: pending, processing, completed, failed percentage (Optional[int]): Progres…
2 properties
1 required
OverallEmotions
object
Overall emotions across modalities.
3 properties
GenerateCSVResponse
object
Response after generating a CSV report. Attributes: id (str): ID of the resource associated with the CSV. message (str): Confirmation or status message. status…
3 properties
3 required
EmotionScores
object
Emotion scores representing the intensity of each emotion. All scores must be non-negative integers.
8 properties
ValenceArousalIntensity
object
Model representing emotional intensity values. Attributes: valence (float): Positive or negative emotion scale. arousal (float): Energy or excitement level. in…
3 properties
3 required
PersonalitySegmentItem
object
Individual segment data with OCEAN metrics. Attributes: segmentid (int): Unique identifier for this segment startmillis (int): Segment start time in millisecon…
4 properties
4 required
PersonalityAnalysisResponse
object
Complete response for personality analysis retrieval (public API). Attributes: videoid (str): Video identifier faceid (int): Face identifier (must be = 1) anal…
5 properties
2 required
HTTPValidationError
object
1 property
Body_trigger_personality_analysis_v2_videos__video_id__personality_analyze_post
object
3 properties
1 required
PersonalityOverallMetrics
object
Overall personality analysis metrics. Attributes: oceanmetrics (PersonalityOceanMetrics): OCEAN personality trait scores
1 property
1 required
FramesResponse
object
Model for a single video frame with face data. Attributes: originalframeimage (str): Unprocessed frame image. frameimage (str): Processed frame image with anno…
7 properties
Body_edit_title_or_description_by_id_v1_videos__video_id__metadata_put
object
2 properties
MergeResponse
object
Response model for merging video/audio content. Attributes: message (str): Status message about the merge result.
1 property
1 required
FaceNameItem
object
Represents a mapping between a face ID and its assigned name. Used for labeling or identifying detected faces.
2 properties
1 required
SpeakerFaceMatchResponse
object
Response model for the result of speaker-face matching operations. Attributes: status (str): Status of the operation (e.g., "completed"). message (str): Inform…
2 properties
2 required
Specification
The full machine-readable OpenAPI contract behind this narrative.
Source
More from Imentiv AI 5
Other APIs Imentiv AI publishes across the network.
Imentiv AI AI Insights API API
Imentiv AI Audio Emotion API API
Imentiv AI Image Emotion API API
Imentiv AI Report API API
Imentiv AI Text Emotion API API
#Video Emotion API