Highlight detection
Transcribes long recordings and identifies candidate moments so creators can review selected segments instead of scanning the entire source manually.
SupoClip
SupoClip is an open-source AI video clipper that finds candidate moments in long videos, reframes them for vertical viewing, and adds synchronized captions. It is designed for creators and teams repurposing YouTube videos or uploaded recordings for Shorts, TikTok, and Reels.
Open-source AI clipping for short-form video
SupoClip is an open-source AI video clipper for turning long recordings and YouTube videos into short-form vertical content. It combines transcription, candidate-segment detection, scoring, face-aware reframing, captions, and export settings in one workflow for YouTube Shorts, TikTok, and Instagram Reels.
Users can paste a YouTube URL or upload a video file, review the moments identified by the system, and render selected clips in a captioned 9:16 format. The application is available as a hosted service, while the AGPL-3.0 codebase can be self-hosted and adapted for teams that want control over infrastructure, model providers, or processing behavior.
AI-assisted clipping and short-form production
Virality scoring
Rates candidate clips from 0 to 100 using factors including hook strength, engagement, value, and shareability; the score is intended to prioritize review.
Face-aware vertical cropping
Uses MediaPipe and OpenCV to detect and track faces when converting footage to a vertical 9:16 frame, with manual review still useful for multi-person scenes and screen shares.
Word-synced captions
Creates animated subtitles using word-level timestamps and includes caption templates, font presets, and adjustable styling options.
B-roll overlays
Can automatically source and overlay relevant stock footage from Pexels when using the hosted workflow described on the site.
Platform export presets
Provides export presets for TikTok, Instagram Reels, and YouTube Shorts, with platform-oriented encoding settings.
Practical ways to use SupoClip
Repurpose podcasts and interviews
Process podcast or interview recordings into a set of candidate Shorts, then review context, speaker framing, and captions before publishing the strongest excerpts.
Create educational snippets
Turn lectures, tutorials, or talks into focused clips organized around individual explanations or ideas rather than editing the full recording manually.
Extend founder and brand content
Give founders and marketing teams a repeatable workflow for extracting product explanations, customer-facing insights, or event highlights from long-form recordings.
Run a controlled internal clipping pipeline
Use the hosted application for a simpler workflow, or deploy the open-source stack on team infrastructure when provider choice, source access, or customization is important.
Experiment with local processing
Build a local or customized processing setup with Docker Compose, Ollama, and local Whisper transcription when reducing reliance on external model providers is a priority.
Pros and Cons
Pros
- Open-source AGPL-3.0 codebase can be inspected, modified, forked, and self-hosted.
- Combines highlight detection, scoring, face-aware 9:16 reframing, captioning, and social export presets in one workflow.
- Supports both YouTube URLs and uploaded video files as source inputs.
- Can use hosted or local model configurations, including Ollama for clip selection and local Whisper transcription.
Cons
- Self-hosting requires users to manage compute, storage, environment variables, background jobs, and provider configuration.
- The self-hosted setup may still involve paid transcription or AI-provider usage, even though the source code is free.
- AI-selected moments, automated crops, captions, and scores require human review before publishing, particularly for complex scenes or accuracy-sensitive content.
FAQ
Can SupoClip turn YouTube videos into Shorts?
Yes. SupoClip accepts a YouTube URL, transcribes the source, proposes candidate segments, and can render selected moments as vertical, captioned clips.
Does SupoClip add captions to generated clips?
Yes. It generates word-synced subtitles and provides caption templates with adjustable font, color, and output settings before rendering.
How can SupoClip be self-hosted?
The documented full-stack setup uses Docker Compose and includes a Next.js frontend, FastAPI backend, background workers, PostgreSQL, and Redis. Developers can also run these components separately.
Is SupoClip free to self-host?
Self-hosting is free under the AGPL-3.0 license, but users provide their own compute, storage, transcription service, and language-model configuration. SupoClip also offers a hosted version for users who do not want to manage infrastructure.
Can SupoClip guarantee that an AI-selected clip will perform well?
No. Virality scoring is a review aid based on factors such as hook strength, engagement, value, and shareability. Creators should review context, caption accuracy, framing, and audience fit before publishing.
Quick Facts
- Category
- AI video editing
- Primary workflow
- Long video to captioned vertical clips
- Source inputs
- YouTube URLs and uploaded video files
- Output platforms
- YouTube Shorts, TikTok, and Instagram Reels
- Deployment
- Hosted application or self-hosted with Docker Compose
- License
- AGPL-3.0
Альтернативы SupoClip
Zella
Zella is a screen recorder and on-device AI video editor for Mac and iPhone. It helps creators record screens or cameras, automatically clean up footage, add captions, reframe clips, and export videos without uploading the core project to the cloud.
Tactiq
Tactiq is an AI note taker for Google Meet, Zoom, and Microsoft Teams that transcribes meetings live and turns them into summaries, action items, and follow-up outputs. It is built around a Chrome extension and supports team workflows through sharing and integrations.
CAMB.AI Streams
CAMB.AI Streams dubs live audio in multiple languages in real time for broadcasts on platforms like YouTube, Twitch, and X. It plugs into existing live workflows using common streaming protocols and avoids a post-production step.
CAKIE
CAKIE is a Mac app for recording your screen and voice for an AI agent. It adds a transcript and screenshot highlights, then lets you copy a prompt and paste or attach the context in another AI app.
SpeakoFlow
SpeakoFlow is a free, open-source desktop voice-to-text app for Windows, macOS, and Linux. It supports dictation into any app, voice-driven writing with Flow, cleanup, translation, and a screen-aware assistant.
Video Effects SDK
Video Effects SDK adds real-time webcam effects such as background blur, background replacement or removal, denoising, framing, beautification, and color grading. It is built for teams shipping live video experiences on web, desktop, and mobile platforms.