README / README.md
tony158's picture
Org card: clearer preset order
530ff5e verified
|
Raw History Blame Contribute Delete
5.91 kB
---
title: README
emoji: 🎬
colorFrom: green
colorTo: yellow
sdk: static
pinned: false
short_description: 'Open-source video pipeline: clipper, AI video & more'
---
<p align="center">
<img src="https://viralmint.net/icon-192.png" width="88" alt="ViralMint logo">
</p>
<h1 align="center">ViralMint</h1>
<p align="center">
<b>Open-source video pipeline: clipper, AI video &amp; more.</b><br>
Scout trends, cut clips, write and voice scripts, caption and render, on your own computer.
</p>
<p align="center">
<a href="https://viralmint.net/">Website</a> ·
<a href="https://github.com/openclaw-easy/ViralMint">GitHub</a> ·
<a href="https://viralmint.net/mcp/">MCP server</a> ·
<a href="https://www.youtube.com/@ViralMintNet">YouTube</a> ·
<a href="https://x.com/ViralMintNet">X</a>
</p>
<p align="center">
<a href="https://github.com/openclaw-easy/ViralMint"><img src="https://img.shields.io/github/stars/openclaw-easy/ViralMint?style=flat&logo=github&label=GitHub&color=34d399" alt="GitHub stars"></a> <a href="https://github.com/openclaw-easy/ViralMint/releases/latest"><img src="https://img.shields.io/github/v/release/openclaw-easy/ViralMint?label=release&color=34d399" alt="Latest release"></a> <a href="https://github.com/openclaw-easy/ViralMint/blob/main/LICENSE"><img src="https://img.shields.io/badge/licence-AGPL--3.0-34d399" alt="Licence: AGPL-3.0"></a> <a href="https://github.com/openclaw-easy/ViralMint/releases/latest"><img src="https://img.shields.io/badge/macOS%20%C2%B7%20Windows%20%C2%B7%20Linux-desktop-34d399" alt="Runs on macOS, Windows and Linux"></a>
</p>
<p align="center">
<img src="https://viralmint.net/screenshots/clip-studio.webp" width="760" alt="ViralMint Clipper: a long video on a timeline with AI-suggested clip ranges">
</p>
## What ViralMint does
ViralMint is a desktop app for macOS, Windows and Linux. It runs a local server and opens in your browser, and the heavy lifting (Whisper, ffmpeg, rendering) happens on your machine.
| Studio | What it does |
|---|---|
| **Scout** | Find outlier videos in a niche on YouTube, TikTok and Douyin, scored against each channel's median views |
| **Clipper** | Turn a long video into vertical shorts, with AI-suggested moments, shot-aware face reframing and captions |
| **Smart Video** | Script → voice → matched stock or AI visuals → word-by-word captions → MP4, editable scene by scene |
| **AI Video & Image** | Text- and image-to-video, AI images and thumbnails through one account |
| **Motion Graphics** | AI-authored motion graphics rendered locally with HyperFrames |
| **Voice** | 400+ text-to-speech voices, and voice cloning that runs fully on-device |
| **Tools** | 40+ single-purpose tools: captions, subtitles, translate, reframe, remove silence, auto-zoom and more |
| **MCP** | 150+ tools exposed to Claude Code, Cursor and any MCP client |
## Try it in your browser
<p align="center">
<a href="https://huggingface.co/spaces/ViralMintNet/word-by-word-captions"><img src="https://huggingface.co/spaces/ViralMintNet/word-by-word-captions/resolve/main/captions-preview-6.gif" width="744" alt="Six clips with captions that highlight each word as it is spoken, one per preset"></a>
</p>
**[Word-by-Word Captions](https://huggingface.co/spaces/ViralMintNet/word-by-word-captions)** is ViralMint's caption engine running in your browser. Drop in a short video and Whisper (through Transformers.js) transcribes it locally; you get TikTok-style captions where each word lights up, a live preview, and `.ass` / `.srt` files. Nothing is uploaded.
The clips above show its six presets, left to right with the top row first: **brainrot**, **bold**, **neon**, **viral**, **karaoke** and **minimal**.
<p align="center">
<a href="https://huggingface.co/spaces/ViralMintNet/word-by-word-captions"><img src="https://huggingface.co/datasets/huggingface/badges/resolve/main/open-in-hf-spaces-md-dark.svg" alt="Open in Spaces"></a>
</p>
## A look inside
<table>
<tr>
<td width="50%"><img src="https://viralmint.net/screenshots/smart-video.webp" alt="Smart Video: a script turned into scenes with voice, stock footage and captions"><br><b>Smart Video</b>: a script becomes scenes with a voice, matched footage and captions, editable one scene at a time.</td>
<td width="50%"><img src="https://viralmint.net/screenshots/ai-video.webp" alt="AI Video studio with templates and model tiers"><br><b>AI Video</b>: text- and image-to-video with templates, from budget to flagship models.</td>
</tr>
<tr>
<td width="50%"><img src="https://viralmint.net/screenshots/motion-graphics.webp" alt="Motion Graphics editor with code, preview and timeline"><br><b>Motion Graphics</b>: AI-written HyperFrames compositions, previewed and rendered on your machine.</td>
<td width="50%"><img src="https://viralmint.net/screenshots/tools.webp" alt="The tools hub listing single-purpose video tools"><br><b>Tools</b>: 40+ one-job tools, from captions and translation to reframing and silence removal.</td>
</tr>
</table>
## Open models we build on
- **Speech-to-text:** [Whisper](https://huggingface.co/openai/whisper-base) through [faster-whisper](https://github.com/SYSTRAN/faster-whisper) on the desktop and [Transformers.js](https://huggingface.co/docs/transformers.js) in the browser
- **Voice cloning:** [VoxCPM](https://huggingface.co/openbmb/VoxCPM-0.5B), run locally through a ggml port
- **Face tracking for reframing:** [YuNet](https://github.com/opencv/opencv_zoo/tree/main/models/face_detection_yunet) from OpenCV Zoo
- **Motion graphics:** [HyperFrames](https://github.com/heygen-com/hyperframes) by HeyGen
## Licence and contact
The open-source core is on [GitHub](https://github.com/openclaw-easy/ViralMint) under **AGPL-3.0**, and so is the captions Space. Issues and pull requests are welcome.
Questions: [support@viralmint.net](mailto:support@viralmint.net)