GitHub Hot Board

GitHub Hot Board · Архів репозиторію

6v17/VideoSeek

Offline video material retrieval platform for semantic search, subtitle search, Agent API, and AI-assisted editing. (Опис узято з самого репозиторію.)

Дані на October 226v17

Найкраще місце

#25

Недооцінені перлини

100

Усього зірок

18

Усього форків

1

Днів у рейтингах (30 дн.)

Документація проєкту

VideoSeek

License: AGPL-3.0 Platform Release

中文说明 | English

Search a local video library by text or screenshot, with hard-subtitle OCR; preview hits and export MP4, Jianying, or NLE timelines.
Indexing runs on your machine (ONNX · Lance · FFmpeg); your media is not uploaded.

Free forever. Do not pay for resale or “paid install” copies — get it from GitHub / the site.

Download · Releases · User guide (ZH) · QQ 1033551438

VideoSeek search UI


Features

  • Text & image search — Natural language or a reference image to find similar shot time ranges
  • Hard-subtitle OCR — Keyword search over on-screen dialogue
  • Libraries & scope — Multiple libraries, selected videos, search presets
  • Preview & export — Timeline preview; MP4; Jianying draft / Premiere XML / DaVinci FCPXML
  • Local-first — Data stays on disk; optional LAN search and localhost Agent API

Optional: video understanding, tag search, multiple CLIP-family models, experimental recap cuts, and more. Main path: sync → search → export.

Use cases

You have… You want…
Large local or NAS libraries Find shots by semantics, not filenames
Dialogue or hard subs you remember Jump to timestamps after OCR keyword search
An editing workflow Rough-locate clips, then open Jianying / PR / DaVinci

Quick start (installer)

  1. Download from lv17.top or Releases
  2. On first launch, import runtime assets when prompted (models, FFmpeg; OCR pack if you need subtitles)
  3. Sidebar Local Library → add a folder → select videos → Sync selected
  4. Search → query → preview → export

Quick start (from source)

Windows 10/11 recommended. Other OS: see docs/quickstart.md.

pip install -r requirements.txt
python main.py
conda env create -f environment.yml
conda activate VideoSeek
Missing Action
Models / FFmpeg In-app import, 123 cloud zip, or models release
VLC (Windows source only) vlc_lib release → extract at repo root

Fallback: if the model zip and ffmpeg.exe are already on disk, close VideoSeek, download import_runtime_resources.py, and run (no git checkout; writes %LOCALAPPDATA%\VideoSeek):

python import_runtime_resources.py openai-clip.zip ffmpeg.exe

Documentation

Community

  • QQ group: 1033551438
  • GitHub Issues — bugs, source builds, Agent API

License

AGPL-3.0 © 2026 6v17

Support

Support

Поточні місця

  • 25

    Недооцінені перлини

    100 зірок · 18 fork · Усього зірок (за зростанням)

    Недооцінені →

Динаміка за 30 днів

Накоплені зірки

Динаміка місць

← До рейтингів