# ViralCutter

> ViralCutter (0.8 alpha) is a Python/Gradio WebUI and CLI that picks hooks from a long video with Gemini, GPT-4 or a local GGUF model, transcribes with WhisperX, auto-crops to 9:16 with face tracking or a two-person split screen, and burns word-by-word captions; it can also translate captions and export Premiere Pro XML. GPL-3.0. Install scripts are Windows .bat files; a Colab notebook is offered. NVIDIA GPU strongly recommended. No virality score and no direct social upload (on the roadmap). No tagged releases.

- Repository: https://github.com/RafaelGodoyEbert/ViralCutter
- Official docs: https://github.com/RafaelGodoyEbert/ViralCutter/blob/main/README_en.md
- Checked: 2026-10-16

## What it replaces
- Opus Clip: AI picks highlight clips from a long video, Auto-reframe to vertical 9:16 (speaker or face tracking), Animated burned-in captions on clips (partial). Covers picking, reframing and captions locally; no virality score or social publishing, and it is alpha software.

## Facts, with sources

| Question | Status | Answer | Source | Checked |
|---|---|---|---|---|
| Runs on my machine? | Confirmed | Yes, local WebUI or CLI; the LLM can be a local GGUF model or a cloud API | https://github.com/RafaelGodoyEbert/ViralCutter/blob/main/README_en.md | 2026-10-15 |
| Code licence | Partial | GPL-3.0 (copyleft) | https://github.com/RafaelGodoyEbert/ViralCutter/blob/main/LICENSE | 2026-10-15 |
| Model weights licence | 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 | https://github.com/deepinsight/insightface#license | 2026-10-16 |
| Commercial use | Partial | GPL-3.0 code allows commercial use with copyleft conditions; licences of the models it uses are not stated | https://github.com/RafaelGodoyEbert/ViralCutter/blob/main/LICENSE | 2026-10-15 |
| Paid services needed? | Confirmed | None required; Gemini (free key) or GPT-4 optional, or run fully offline with local GGUF models | https://github.com/RafaelGodoyEbert/ViralCutter/blob/main/README_en.md | 2026-10-15 |
| Hardware | Confirmed | NVIDIA GPU with CUDA 12.4+ strongly recommended; exact VRAM and RAM not stated | https://github.com/RafaelGodoyEbert/ViralCutter/blob/main/README_en.md | 2026-10-15 |
| Operating systems | Partial | Windows install scripts documented; Google Colab notebook; macOS and Linux not documented | https://github.com/RafaelGodoyEbert/ViralCutter/blob/main/README_en.md | 2026-10-15 |
| Setup effort | Confirmed | Medium; needs Python 3.10/3.11, FFmpeg, NVIDIA drivers and C++ Build Tools, then a .bat installer | https://github.com/RafaelGodoyEbert/ViralCutter/blob/main/README_en.md | 2026-10-15 |

GitHub: 424 stars, 99 forks, last push 2026-09-10, archived: no.
---
Source: RepoQuarry (https://repoquarry.dev/projects/viralcutter). Data licence: CC BY 4.0. Quotes are from project documentation and belong to their authors.