        
        Native macOS  ·  for editors, DITs & archivists
      

Find the shot,
not the file.

videoscriber watches every clip in your library and writes a structured description next to it — so you search 2,000 files by what's in the frame, not by squinting at filenames.

Buy License — $79 See how it works

Enterprise Grade · macOS 13+ · Apple Silicon

Queue Library

+ ✓ videoscriber ✓ dev@local

Running

6559929…25fps.mp4 MiniMax-M3

5035831…25fps.mp4 MiniMax-M3

Queued

8680227…25fps.mp4 MiniMax-M3

9155281…25fps.mp4 MiniMax-M3

13603938…30fps.mp4 MiniMax-M3

874118…mp4 kimi-latest

Done

✓ 14764954…24fps.mp4 MiniMax-M3

Festive Day-of-the-Dead street with towering…

✓ 8747386…30fps.mp4 MiniMax-M3

Aerial drone view of a single white car…

✓ 20073502…24fps.mp4 MiniMax-M3

Backlit portrait of a woman with natural curls…

14764954_1920_1080.mov

Reveal in Finder

MiniMax (Anthropic-compatible) · MiniMax-M3 · standard · adaptive

✓ Done

                ▾
                
                Frames sent to model (11)

00:00.000

00:01.000

00:02.000

00:03.000

00:04.000

Markdown JSON Source

14764954_1920_1080

Summary

A festive colonial pedestrian street lined with towering skeleton figures, papel picado banners, and marigolds — passers-by drift through the afternoon sun. Vivid, cultural, lightly macabre.

Establishing wide of a Day-of-the-Dead street celebration in warm afternoon light.

The Library

Describe once. Search forever.

Point the Library at a folder and every described clip becomes findable — fuzzy search across themes, settings, keywords and transcripts, plus structured filters for shot, time, lighting and environment.

Queue Library

Library ✓ dev@local

Open Folder… Recursive /Users/jared/Downloads/videoscriber-stock-footage

warm afternoon street, festive ×

Theme ▾ Shot ▾ Time ▾ Lighting ▾ Environment ▾ Keyword ▾ Clear filters

Time: afternoon ×

14 clips · 0 flagged · 0 need review · 3 of 14 match

0:11

14764954_1920_1080.mp4 98% match

Festive outdoor pedestrian street with large skeleton figures and marigolds, evoking a Day of the Dead celebration.

medium afternoon colorful colonial street with skeleton figures & marigolds

0:09

20073502_1080_1920.mp4 94% match

Backlit medium-close of a woman with natural curls in a blush dress, dappled light beneath a tree.

medium-close afternoon park, dappled light through trees

0:15

9155281_2160_4096.mp4 71% match

Editorial close-up of a woman's face with water on her skin, dim and intimate studio light.

close dim-interior studio, soft low light

Build _INDEX.json + _INDEX.md Re-rate flagged Include refusals

How it works

Three steps. Nothing leaves your Mac except the frames.

You bring your own AI key. Frames go straight to your provider — never through our servers.

01

Drop your footage

Drag one clip or a whole folder onto the window. videoscriber queues everything and shows you the exact frames it analyzes.

02

AI describes each clip

Representative frames go to Claude, GPT, or a local model. Back comes structured metadata: shot type, motion, people, setting, palette, mood.

03

Search by content

A .description.json sits next to every clip. Grep it, pipe it to an LLM, or hit it from Spotlight.

What it writes

Not a tag soup. A real schema.

Every clip gets the same structured object — JSON as the source of truth, Markdown for humans. Greppable, diff-able, and ready to feed straight into another LLM.

11 frames analyzed

14764954_1920_1080.mov

duration00:11.0
resolution1920×1080
codecH.264 · avc1

.description.json .description.md

"A festive colonial pedestrian street lined with towering skeleton figures, papel picado banners, and marigolds — passers-by drift through the afternoon sun. Vivid, cultural, lightly macabre."

shot type

medium

camera motion

static

people

14 · perceived

location

outdoor

time of day

afternoon

mood

festive, macabre

dominant palette

#E8D8A6

#9B4A3A

#F2F2F2

#6FA85B

#2A6B9C

search keywords

day of the dead skeleton figures papel picado marigolds mexican folk art cultural celebration

engine: minimax-m3 · 11 frames · adaptive sampling

Features

Built for working editors.

Not a subscription dashboard. A quiet utility that lives next to Premiere, Resolve, and FCP.

Structured sidecar files

A .json and .md next to each clip. No database, no import — just files you own.

Rich shot metadata

Shot type, camera motion, people, setting, color palette, mood, and suggested use cases — with controlled vocabularies for the core shot dimensions, all greppable and diff-able.

Batch the whole drive

Drop 500 clips and walk away. The queue runs with configurable concurrency and survives restarts — resuming right where it left off.

Bring your own key

Frames go from your Mac straight to your provider. We never see your footage, your key, or your bill — and neither does anyone else.

Native macOS

A real SwiftUI app — no Electron, no browser, no web server. AVFoundation for frame extraction. Ventura or newer, Apple Silicon.

Described, never identified

People are described by appearance, mood, and wardrobe — never named. Person attributes are framed as "perceived," with a confidence score on mood.

Spoken-word transcripts

Optional audio pass via Whisper, Deepgram, or fully on-device speech. The transcript lands on the sidecar and becomes part of what you search.

Cut-ready exports

Hand off straight to the timeline — FCPXML, EDL, and CSV markers for Premiere, Resolve, and Final Cut. Your descriptions become editable clips and markers.

Semantic search

Hybrid embedding + keyword ranking finds the shot by meaning, not just exact words — "warm golden-hour street" surfaces the right clip even when the words don't match.

Watch folders

Point it at an ingest folder and new clips are described automatically as they land — no dragging, no babysitting the queue.

Faces, on-screen text & location

Optional face detection (counts and boxes — detection only, never recognition), on-screen text OCR, and reverse-geocoded location from clip GPS metadata.

Built for hard-to-catalog footage

An unrestricted cataloging profile for archive, news, and adult-industry editors — pair it with a local model to describe footage hosted models refuse to touch.

Works with any vision model — your key, your bill

Claude GPT-4o / GPT-5 OpenRouter MiniMax M3 Moonshot · Kimi Ollama · local LM Studio · local any OpenAI-compatible

Privacy

Your footage never touches our servers.

There's no upload, no cloud account, no telemetry by default. videoscriber talks directly from your Mac to the provider you chose with the key you own. We physically can't see your clips — and that's the point.

↳ Frames go straight to your provider

↳ Your API key never leaves your Mac

↳ Run a local model to keep frames offline entirely

↳ No telemetry. No crash reporting. Nothing phones home.

Pricing

One price. Yours forever.

No subscription, no seats to manage. A single license unlocks everything.

$79 one-time

One license, bound to your email · use it on every Mac you own

✓ Unlimited descriptions & batch jobs

✓ Every provider, including local models

✓ CLI + macOS app

✓ Use it on every Mac you own — bound to your email

✓ Bring your own AI key — no markup

Buy License — $79

Payments and Licensing via GumRoad

Stop scrubbing.
Start searching.

Turn your unsearchable drive into a library you can actually query — this afternoon.