SupoClip vs OpenShorts vs ViralCutter

Side by side, as alternatives to Opus Clip. Rows that differ are highlighted; the strongest value in a row is marked. Unknown means no source yet.

SupoClipFujiwaraChoki/supoclip

OpenShortsmutonby/openshorts

ViralCutterRafaelGodoyEbert/ViralCutter

Opus Clippaid product

Cost and coverage

Price

$0 software; you run it

See pricing page source ↗

AI picks highlight clips from a long video

Partly

Yes

Auto-reframe to vertical 9:16 (speaker or face tracking)

Partly

Yes

Animated burned-in captions on clips

Partly

Yes

Virality score per clip

Partly

Yes

Schedule and publish clips to social platforms

Partly

Yes

Jobs covered

4 of 5 jobs

3 of 5 jobs

All 5

Popularity and activity (from GitHub)

Stars

1,646

6,909Top

429

—

Gain this week

Unknown

—

Signal

Building history

—

Commits / 4 wk

119Top

—

Latest release

Unknown

—

Commits / 12 wk

177

260

—

People committing / 12 mo

—

Issues opened / closed, 30 days

5 / 19

7 / 9

0 / 0

—

Facts, with sources on each project page

Runs on my machine?Differs

Yes, self-hosted with Docker Compose; a hosted web and iOS version also exists

Yes, self-hosted with Docker Compose; a paid hosted version also exists

Yes, local WebUI or CLI; the LLM can be a local GGUF model or a cloud API

Hosted by the vendor

Code licenceDiffers

AGPL-3.0 (strong copyleft, including network use)

MIT for the core app; the cloud/ folder (billing, hosted infrastructure) is source-available under a commercial licence

GPL-3.0 (copyleft)

—

Model weights licenceDiffers

No separate model weights; uses the LLM and transcription services you configure

No separate model weights; downloads third-party models (faster-whisper, YOLOv8, MediaPipe) and calls the LLM you choose

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

—

Commercial useDiffers

Allowed under AGPL-3.0 conditions; offering a modified version over a network means sharing its source

Yes for the MIT core; the cloud/ billing folder may not be resold as a hosted service. Licences of bundled models (e.g. ultralytics YOLOv8) not checked

GPL-3.0 code allows commercial use with copyleft conditions; licences of the models it uses are not stated

—

Paid services needed?Differs

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

Clipping can run with a local LLM and no paid key; Gemini is the default and is needed for auto-layout and silent videos; posting, dubbing and AI actors use paid APIs

None required; Gemini (free key) or GPT-4 optional, or run fully offline with local GGUF models

Subscription

HardwareDiffers

Runs on CPU by default (CPU-only Torch build, Apple silicon included); NVIDIA CUDA path optional. No RAM figure

8GB+ RAM; CPU works (5-8 min per 8-min video); optional NVIDIA GPU, 8GB VRAM enough for large-v3-turbo

NVIDIA GPU with CUDA 12.4+ strongly recommended; exact VRAM and RAM not stated

—

Operating systemsDiffers

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

Runs in Docker; Linux and Windows (Docker Desktop with WSL2) are documented; macOS not mentioned

Windows install scripts documented; Google Colab notebook; macOS and Linux not documented

—

Setup effortDiffers

Medium, Docker Compose with a .env of API keys

Medium, docker compose up --build, then enter API keys in the dashboard

Medium; needs Python 3.10/3.11, FFmpeg, NVIDIA drivers and C++ Build Tools, then a .bat installer

—

Stars over time

Switch to Growth % to compare projects of different sizes fairly.

SupoClip
OpenShorts
ViralCutter

Focus a point, use arrow keys, or tap for its value.

Tracked daily since 16 Oct 2026. Dashed history: estimated from public records of when people starred the repo. Lines connect observations only; gaps contain no measured points.

Growth % starts at each project's first observed point in the shown range. Zero-star starts are unavailable.

Notes for a video or post

A plain summary with today's date and a link to the sources. Check each project page before you publish.

SupoClip vs OpenShorts vs ViralCutter (as alternatives to Opus Clip)
Figures from RepoQuarry, 21 Oct 2026. Sources: https://repoquarry.dev/compare?ids=supoclip,openshorts,viralcutter&product=opus-clip

Opus Clip: See pricing page
SupoClip: free software; does 4 of 5 Opus Clip jobs
OpenShorts: free software; does 4 of 5 Opus Clip jobs
ViralCutter: free software; does 3 of 5 Opus Clip jobs

- SupoClip: 1,646 GitHub stars, 177 commits in 12 weeks, licence AGPL-3.0 (strong copyleft, including network use)
- OpenShorts: 6,909 GitHub stars, 260 commits in 12 weeks, licence MIT for the core app; the cloud/ folder (billing, hosted infrastructure) is source-available under a commercial licence
- ViralCutter: 429 GitHub stars, 2 commits in 12 weeks, licence GPL-3.0 (copyleft)

Where they differ:
- Runs on my machine?: SupoClip Yes, self-hosted with Docker Compose; a hosted web and iOS version also exists; OpenShorts Yes, self-hosted with Docker Compose; a paid hosted version also exists; ViralCutter Yes, local WebUI or CLI; the LLM can be a local GGUF model or a cloud API
- Code licence: SupoClip AGPL-3.0 (strong copyleft, including network use); OpenShorts MIT for the core app; the cloud/ folder (billing, hosted infrastructure) is source-available under a commercial licence; ViralCutter GPL-3.0 (copyleft)
- Model weights licence: SupoClip No separate model weights; uses the LLM and transcription services you configure; OpenShorts No separate model weights; downloads third-party models (faster-whisper, YOLOv8, MediaPipe) and calls the LLM you choose; ViralCutter 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
- Commercial use: SupoClip Allowed under AGPL-3.0 conditions; offering a modified version over a network means sharing its source; OpenShorts Yes for the MIT core; the cloud/ billing folder may not be resold as a hosted service. Licences of bundled models (e.g. ultralytics YOLOv8) not checked; ViralCutter GPL-3.0 code allows commercial use with copyleft conditions; licences of the models it uses are not stated
- Paid services needed?: SupoClip 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; OpenShorts Clipping can run with a local LLM and no paid key; Gemini is the default and is needed for auto-layout and silent videos; posting, dubbing and AI actors use paid APIs; ViralCutter None required; Gemini (free key) or GPT-4 optional, or run fully offline with local GGUF models
- Hardware: SupoClip Runs on CPU by default (CPU-only Torch build, Apple silicon included); NVIDIA CUDA path optional. No RAM figure; OpenShorts 8GB+ RAM; CPU works (5-8 min per 8-min video); optional NVIDIA GPU, 8GB VRAM enough for large-v3-turbo; ViralCutter NVIDIA GPU with CUDA 12.4+ strongly recommended; exact VRAM and RAM not stated
- Operating systems: SupoClip 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; OpenShorts Runs in Docker; Linux and Windows (Docker Desktop with WSL2) are documented; macOS not mentioned; ViralCutter Windows install scripts documented; Google Colab notebook; macOS and Linux not documented
- Setup effort: SupoClip Medium, Docker Compose with a .env of API keys; OpenShorts Medium, docker compose up --build, then enter API keys in the dashboard; ViralCutter Medium; needs Python 3.10/3.11, FFmpeg, NVIDIA drivers and C++ Build Tools, then a .bat installer

Stars show popularity, not quality. Check each project page before publishing.

Want share images and a ready video description? Open a project's creator kit.

Numbers: GitHub, fetched nightly. Facts: read from each project's own documentation, with the source on its page. How we check. FujiwaraChoki/supoclip ↗mutonby/openshorts ↗RafaelGodoyEbert/ViralCutter ↗

SupoClip vs OpenShorts vs ViralCutter

Stars over time

Notes for a video or post

Cookie preferences

Report a problem