100% Local · No Internet · Native macOS

Your footage.
Your machine. Your rules.

Catalog, transcribe and semantically search your videos and photos — using DETR, CLIP and Whisper, entirely on your Mac. No uploads, no cloud, no compromises.

Apple Silicon & Intel · macOS 13+

AI Video Scanner Pro
AI Video Scanner Pro — scanner view con analisi AI completata

FEATURES

A creative engine that understands every frame.

AI Video Scanner Pro — schermata principale di scansione semantica

Dominant Colorimetry

Local color grading analysis and dominant palette mapping for every clip.

Colorimetria dominante — palette hex con percentuali

Local Audio Transcription

Whisper extracts, transcribes and anchors speech timestamps — fully local. Pick the audio language per scan (auto-detect, Italian or English), tune anti-hallucination controls, edit any segment with the pencil icon and export the transcript to TXT or SRT in one click.

Audio Transcription — trascrizione con timestamp

Smart Local Search

Search by title, notes, AI tags, spoken phrases, color or geographic location. Instant results across the whole archive.

Smart Search — ricerca semantica nei video analizzati

Semantic Video Scanning

AI understands what happens inside your videos with custom descriptive prompts. Search scenes, actions, moods.

Semantic Video Scanning — tag AI su frame con CLIP e DETR

AI Vision Object Tagging

Automatic recognition of objects, people and tools via DETR by Meta AI, executed fully on-device.

AI Vision — timeline con tag oggetti per frame

Video Library

All your videos in a searchable archive. Grid or list view with AI tags, duration, capture date, GPS location and an audio-track badge. Multi-select for bulk deletion. Open the file's containing folder directly from the library with one click.

Video Library — vista lista con tag AI

GPS & Capture Date

Original capture date/time and GPS coordinates extracted automatically from videos and photos (iPhone, Samsung, GoPro, DJI). In-app location map with one-tap open in Apple Maps or Google Maps.

GPS Metadata — coordinate geografiche e mappa statica

Batch Processing

Scan multiple videos or an entire folder in one operation. Smart queue with per-file progress tracking.

Batch Processing — coda completata

Photo Library

Analyze your photos with the same AI pipeline as videos — CLIP, DETR and colorimetry. Organize them into projects, search by tag, color or location, browse in grid or list view.

Photo Library — progetti foto con AI Vision

PRICING

Buy once. Yours forever.

No subscriptions. One-time license.

Compare before you decide.

Twelve Labs: $0.042/min indexed — on 100h that's $252/mo
Mixpeek: from $2,000/month flat rate
AI Video Scanner Pro: one purchase, forever.
🎉 Launch Offer
Offer ends in:
09days
13hours
14min
48sec

Trial

10-day full trial, free.

Free
Download free
  • Full video & photo analysis for 10 days
  • Full audio transcription (Whisper)
  • Photo Library with CLIP + DETR
  • Semantic and color search
  • No credit card required
Most popular

PRO License

Unlock the full power of the engine.

€59.99€99one-time · lifetime
Buy PRO
  • Unlimited video archive
  • Photo Library with AI Vision
  • Full Whisper transcription
  • DETR AI Vision + advanced colorimetry
  • Unlimited semantic & color search
  • Lifetime updates
  • Instant AIVS-XXXX license key
Privacy First

Privacy by design. By construction.

All AI — DETR by Meta AI, OpenAI CLIP and Whisper — runs natively on your Mac. Your videos never leave your device. Ever.

Zero uploads

No cloud, no servers.

Offline first

Works without a connection.

Open models

DETR + CLIP + Whisper, on-device.

FAQ

Everything you need to know.

BUILT-IN AI MODELS

Three AI models. All local. All yours.

No external models, no pay-per-call API. Weights are bundled inside the app and run directly on your Mac.

Audio

Audio Transcription

OpenAI Whisper extracts and transcribes speech with second-accurate timestamps, in Italian, English and 90+ languages.

openai/whisper-base · MIT
Vision

Object Detection

DETR by Meta AI automatically recognizes people, objects and scenes in every frame. 80 COCO classes, Apache 2.0 license.

facebook/detr-resnet-50 · Apache 2.0
Semantic

Semantic Search

OpenAI CLIP turns your descriptions into visual searches. Type 'sunset over the sea' and find every matching scene in your archive.

openai/clip-vit-base-patch32 · MIT

All models are open-source under MIT or Apache 2.0 licenses — compatible with proprietary commercial distribution.