- Home
- AI Video Summarizers
- VideoHighlighter
VideoHighlighter
What it is
VideoHighlighter is a local desktop app for analyzing videos and producing highlight reels or individual clips. It scores scenes using motion, audio, objects, actions, and transcript signals, then explains the scoring in timelines and reports. Reports can show per-signal points, fired signals, strong moments omitted from the result, and transcript claims that were not measured. Video files, transcripts, detections, and local models remain on disk, and analysis, search, and export do not upload footage. The basic pipeline needs no API key, and a GPU is optional because current CPUs can run it. Free capabilities include offline analysis, face detection, VR side-by-side playback, CLIP search, composition rules, model training, and a model hub. Pro adds object and action overlays, custom categories, similarity search, open-vocabulary detection, and counter or scoreboard detection. Windows and macOS have prebuilt downloads; Linux uses pip and Python. Individual Pro costs $49, paid once.
For and against
For
- Offline analysis keeps footage on disk
- Basic pipeline needs no API key
- Current CPUs can run the pipeline
- Reports explain detection signals
- Supports local files, YouTube, and Twitch VODs
Against
- Linux installation runs from source
- Pro activation needs one internet connection
- Individual license covers one editor
The verdict
VideoHighlighter focuses on local, explainable highlight creation across major desktop platforms. Its free edition is broad, while Pro adds specialized detection and commercial licensing for a one-time fee.
Who it suits
VideoHighlighter suits editors who want local video analysis on Windows, macOS, or Linux. It also fits users who need offline processing, explainable reports, and optional commercial licensing.
Plans and prices
Free
AGPL-3.0 · offline analysis · Windows, macOS, Linux
Read 1 Oct 2026 · github.com
Individual
single editor · up to 5 computers · commercial license · priority support
Read 1 Oct 2026 · aseiel.github.io
Studio
teams and multi-seat deployments · multiple seats · volume pricing
Read 1 Oct 2026 · aseiel.github.io
On the record
- Activation
- Pro activation requires an internet connection once, after which the license is checked locally and the app does not contact the vendor.aseiel.github.io · read 1 Oct 2026
- API requirement
- The basic pipeline needs no API key.github.com · read 1 Oct 2026
- Detection
- The app scores scene, motion, audio, objects, actions and transcript signals, then displays the reasons on a timeline and report.github.com · read 1 Oct 2026
- Explainability
- Reports provide per-signal point breakdowns, fired signals, strong moments that missed the cut and transcript claims that were not measured.github.com · read 1 Oct 2026
- Free capabilities
- The free edition includes offline analysis, live face detection, VR side-by-side playback, CLIP search, composition rules, model training and a model hub.github.com · read 1 Oct 2026
- Hardware
- A GPU is optional; current CPUs run the pipeline, while Intel Arc and other GPUs can accelerate detection.aseiel.github.io · read 1 Oct 2026
- Install platforms
- Prebuilt downloads are available for Windows and macOS, while Linux runs from source with pip and Python.github.com · read 1 Oct 2026
- License
- The free repository is released under the GNU Affero General Public License v3.0, with a separate commercial license offered by the copyright holders.github.com · read 1 Oct 2026
- Offline privacy
- Video files, transcripts, detections and local models stay on disk; analysis, search and export do not upload footage.aseiel.github.io · read 1 Oct 2026
- Pro capabilities
- Pro adds live object and action overlays, point-and-teach categories, find-more-like-this search, open-vocabulary detection and counter or scoreboard detection.aseiel.github.io · read 1 Oct 2026
- Purpose
- VideoHighlighter is a local desktop app that analyzes video and exports highlight reels plus individual clips.github.com · read 1 Oct 2026
- Support
- Support is provided through Discord and email, with priority support for Pro customers and no ticket portal.aseiel.github.io · read 1 Oct 2026
- Technical stack
- The pipeline uses YOLOX with OpenVINO, YuNet and SFace face models, Whisper transcription, a composition engine, CLIP search and a PySide6 editor.aseiel.github.io · read 1 Oct 2026
- Usage limit
- An Individual Pro license is for one editor and may be used on up to five computers.aseiel.github.io · read 1 Oct 2026
