Price
$0 software; you run it
$0 software; you run it
$0 software; you run it
AI picks highlight clips from a long video
Partial: Partly
Partial: Partly
Partial: Partly
Confirmed: Yes
Auto-reframe to vertical 9:16 (speaker or face tracking)
Partial: Partly
Partial: Partly
Partial: Partly
Confirmed: Yes
Animated burned-in captions on clips
Partial: Partly
Partial: Partly
Partial: Partly
Confirmed: Yes
Virality score per clip
Partial: Partly
No: No
Partial: Partly
Confirmed: Yes
Schedule and publish clips to social platforms
No: No
No: No
No: No
Confirmed: Yes
Jobs covered
4 of 5 jobs
3 of 5 jobs
4 of 5 jobs
All 5
Popularity and activity (from GitHub)
Gain this week
Unknown
Unknown
Unknown
—
Signal
Building history
Building history
Building history
—
Commits / 4 wk
119Top
0
17
—
Latest release
Unknown
Unknown
Unknown
—
People committing / 12 mo
5
2
1
—
Issues opened / closed, 30 days
5 / 19
0 / 0
0 / 0
—
Facts, with sources on each project page
Runs on my machine?Differs
Confirmed: Yes, self-hosted with Docker Compose; a hosted web and iOS version also exists
Confirmed: Yes, local WebUI or CLI; the LLM can be a local GGUF model or a cloud API
Confirmed: Yes, runs on your machine; transcription is local, highlight ranking calls a cloud LLM
Hosted by the vendor
Code licenceDiffers
Partial: AGPL-3.0 (strong copyleft, including network use)
Partial: GPL-3.0 (copyleft)
Confirmed: MIT
—
Model weights licenceDiffers
Confirmed: No separate model weights; uses the LLM and transcription services you configure
Partial: InsightFace pretrained models are for non-commercial research; commercial licensing must be obtained separately. Whisper weights are MIT, and user-selected local GGUF or hosted LLM options retain their own terms
Confirmed: No separate model weights
—
Commercial useDiffers
Partial: Allowed under AGPL-3.0 conditions; offering a modified version over a network means sharing its source
Partial: GPL-3.0 code allows commercial use with copyleft conditions; licences of the models it uses are not stated
Confirmed: Yes, MIT (LLM provider terms apply separately)
—
Paid services needed?Differs
Partial: Quick start needs an AssemblyAI key and an LLM key (Ollama allowed); a fully local Whisper + Ollama route is documented in a blog tutorial; Pexels B-roll optional
Confirmed: None required; Gemini (free key) or GPT-4 optional, or run fully offline with local GGUF models
Partial: Needs an LLM API key; Gemini has a free tier with a daily limit, OpenAI and MuAPI are paid
Subscription
HardwareDiffers
Confirmed: Runs on CPU by default (CPU-only Torch build, Apple silicon included); NVIDIA CUDA path optional. No RAM figure
Confirmed: NVIDIA GPU with CUDA 12.4+ strongly recommended; exact VRAM and RAM not stated
Confirmed: Python 3.10+; Whisper runs on CPU or CUDA GPU, model size selectable
—
Operating systemsDiffers
Partial: Official setup uses Docker Desktop/Engine and explicitly documents Apple Silicon running linux/amd64 backend/worker images through emulation, without Apple GPU acceleration; native Windows/Linux host support is not listed
Partial: Windows install scripts documented; Google Colab notebook; macOS and Linux not documented
Confirmed: Windows, Linux and macOS install steps in the README
—
Setup effortDiffers
Confirmed: Medium, Docker Compose with a .env of API keys
Confirmed: Medium; needs Python 3.10/3.11, FFmpeg, NVIDIA drivers and C++ Build Tools, then a .bat installer
Confirmed: Easy-medium, clone, pip install requirements and add an API key to .env (README clone URL uses an older repo name)
—