media

Video
Metadata
Converter

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.

Max file size: 5 GB

Estimated: 30 sec - 3 min per video

5 input formats

How It Works

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

Technical metadata is parsed from the container and codec headers.

Sampled frames are analyzed by a vision model to extract semantic tags and content categories.

Audio metadata including language, speaker count, and music detection is extracted.

All metadata is merged into a structured JSON response with technical and semantic sections.

Code Examples

from mixpeek import Mixpeek

client = Mixpeek(api_key="YOUR_API_KEY")

result = client.convert(
    source="https://example.com/commercial.mp4",
    from_format="video",
    to_format="metadata",
    options={
        "include_technical": True,
        "include_semantic": True,
        "include_safety_check": True,
        "sample_rate": 5
    }
)

print(f"Duration: {result.technical.duration}s")
print(f"Resolution: {result.technical.width}x{result.technical.height}")
print(f"Categories: {result.semantic.categories}")
print(f"Objects: {result.semantic.objects}")

Use Cases

Enrich media asset management systems with automated metadata

Build filterable video catalogs with AI-generated tags and categories

Audit video libraries for technical compliance (codec, resolution, bitrate)

Pre-process video uploads to validate quality and detect content type before ingestion

Supported Input Formats

MP4

MOV

AVI

MKV

WebM

Quick Info

Categorymedia

Max File Size5 GB

Est. Time30 sec - 3 min per video

Extractorvideo-descriptor

Try This Conversion

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

Frequently Asked Questions

Related Converters

Video

Text

Video to Text

Extract spoken dialogue, on-screen text, and scene descriptions from video files using multimodal AI. Produces time-stamped transcripts with speaker diarization and OCR-detected overlays.

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.

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 metadata?

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

VideoMetadataConverter