Mixpeek Logo
    Login / SignupDemo
    media

    Video
    Faces
    Converter

    Detect, track, and extract all faces appearing in a video. Returns aligned face crops, bounding boxes, timestamps, and optional identity embeddings for each detected face. Supports face clustering to group appearances of the same person across the video.

    Max file size: 5 GB
    Estimated: 3-15 min per hour of video
    5 input formats

    How It Works

    1

    Upload a video file or provide a URL to the Mixpeek API.

    2

    Frames are sampled and processed through a face detection model (SCRFD) to locate faces.

    3

    Detected faces are tracked across frames to maintain identity continuity.

    4

    Each unique face is aligned and cropped using facial landmark detection.

    5

    Face identity embeddings (ArcFace 512D) are generated for each unique face, enabling clustering and matching.

    Code Examples

    from mixpeek import Mixpeek
    

    client = Mixpeek(api_key="YOUR_API_KEY")
    

    result = client.convert(
        source="https://example.com/panel-discussion.mp4",
        from_format="video",
        to_format="faces",
        options={
            "cluster_faces": True,
            "include_embeddings": True,
            "min_face_size": 80,
            "sample_fps": 2
        }
    )
    

    print(f"Unique faces found: {len(result.face_clusters)}")
    for cluster in result.face_clusters:
        print(f"  Person {cluster.id}: {cluster.screen_time}s on screen")
        print(f"    First seen: {cluster.first_appearance}s")
        print(f"    Detections: {cluster.detection_count}")

    Use Cases

    Build face-searchable indexes for video libraries and media archives
    Track on-screen talent appearances across advertising campaigns
    Create face-based navigation for interview and panel discussion videos
    Detect and count unique individuals in surveillance or event footage

    Supported Input Formats

    MP4
    MOV
    AVI
    MKV
    WebM

    Quick Info

    Categorymedia
    Max File Size5 GB
    Est. Time3-15 min per hour of video
    Extractorface-identity

    Try This Conversion

    Get started with the Mixpeek API and convert your first file in minutes.

    Frequently Asked Questions

    Related Converters

    Video
    Images

    Video to Keyframes

    Automatically detect scene changes and extract representative keyframes from any video. Each keyframe includes a timestamp, scene label, and optional caption generated by a vision model.

    Video
    Thumbnails

    Video to Thumbnails

    Generate optimized thumbnail images from video files. Uses intelligent frame selection to pick the most visually appealing and representative frames, with optional face detection and composition scoring.

    Video
    Scenes

    Video to Scenes

    Automatically segment videos into individual scenes using visual and audio cue detection. Each scene includes a start and end timestamp, a representative keyframe, a descriptive label, and a confidence score for the detected boundary.

    Video
    Metadata

    Video to Metadata

    Extract comprehensive technical and semantic metadata from video files. Returns codec details, resolution, duration, frame rate, and AI-generated semantic tags including detected objects, scenes, dominant colors, and content categories.

    Image
    Metadata

    Image to Metadata

    Extract comprehensive technical and semantic metadata from images. Returns EXIF data, camera settings, GPS coordinates, and AI-generated semantic tags including detected objects, scene type, dominant colors, and content categories.

    Ready to convert video to faces?

    Start using the Mixpeek Video to Faces in minutes. Sign up for a free API key and follow the documentation to get started.