AI-Powered · No Spoilers · Viral Ready

Turn Movies into
Viral Short Clips
Automatically

Upload any video and let AI transcribe, analyse, and extract the most compelling moments — complete with captions, hashtags, and your watermark. Ready to post in minutes.

4
AI Providers
3
Whisper Modes
4K
Resolution Support
Videos in Parallel

From Upload to Viral in 3 Steps

No manual editing required. The agent handles everything — from speech recognition to clip selection and social caption generation.

1

Upload Your Video

Drop any movie or video file directly from your browser, or select one already on the server. Chunked upload supports files up to 15 GB with zero data loss on refresh.

2

AI Analyses & Selects

Whisper transcribes the audio while scene detection maps the structure. An LLM then picks the most engaging, spoiler-free moments that stand alone without full movie context.

3

Download Ready Clips

Each clip is encoded with your watermark, merged with your end card, and packaged with AI-generated captions, descriptions, and 20 trending hashtags — ready for any platform.

Packed with Smart Features

Every step of the clip creation pipeline is automated, configurable, and production-ready.

psychology

No-Spoiler AI Selection

LLM-powered clip picker avoids climax, twists, and plot reveals. Selects engaging moments from the safe 10–70% timeline window.

closed_caption

Auto Captions & Hashtags

Generates a punchy hook caption, a 2–3 sentence description, and 15–20 trending hashtags for every clip. Download as JSON or ZIP.

branding_watermark

Smart Watermarking

Add text, logo, or movie-name watermarks. Auto-detects letterbox black bars and places overlays within the actual content area at the right scale.

merge_type

End-Card Merge

Drop an end_merge_video.mp4 into the folder and every clip gets it appended — auto-scaled to match the clip's resolution and frame rate.

tab

Tab-Isolated Sessions

Redis-backed sessions give each browser tab its own isolated state. Open the app in two tabs, process different videos simultaneously.

speed

GPU Acceleration

Three Whisper modes: CPU (base), GPU large-v3, and faster-whisper with real-time per-segment progress. CUDA memory is released after each job.

Works With Your Favourite AI

Plug in any provider for clip selection and caption generation. Or run fully offline with Ollama — no API key required.

smart_toy OpenAI GPT-4o
auto_awesome Anthropic Claude
flare Google Gemini
computer Ollama (Local)
block Rule-Based (No AI)

Production-Grade Pipeline

Built for real video workflows. Handles edge cases like non-square pixel ratios, missing audio streams, Windows MAX_PATH limits, and long filenames.

check

Letterbox-Aware Watermarks

Detects black bars and places overlays only within the visible content area.

check

SAR / FPS Normalisation

End-card is automatically re-encoded to match the clip's exact resolution and frame rate.

check

Persistent Session State

Refresh the page at any step — progress, uploads, and results are fully restored.

check

Parallel Multi-Video Processing

Queue multiple videos and process them all simultaneously in background threads.

Clip Agent — Processing
Transcribing audio… 74%
check_circle
Movie_clip_1.mp4
0:45 → 1:10 · 25s · 8.2 MB
Ready
check_circle
Movie_clip_2.mp4
3:12 → 3:37 · 25s · 7.6 MB
Ready
pending
Movie_clip_3.mp4
Selecting segment…
Queue

Built on Proven Tools

Open-source stack that runs on your own hardware — no cloud required.

mic

OpenAI Whisper

State-of-the-art speech recognition for accurate transcription at any language.

video_settings

FFmpeg

Lossless extraction, filter-complex watermarking, and SAR-normalised concat.

storage

Redis

Server-side session storage with 24-hour TTL keeps every tab's state independent.

api

Flask + Python

Threaded background job runner, chunked uploads, and a clean REST API.

Ready to Create Viral Clips?

Open the app, upload your first video, and get AI-generated clips with captions in minutes. No account required.