AI clip generator · cloud or self-hosted

the free open source ai clip generator, built to clip what people actually watch.

Turn long videos into viral 9:16 shorts, or generate UGC marketing videos with AI actors. Online in the cloud with zero setup, or self-hosted with Docker for free.

No credit card required. 20 free minutes every month. Paid plans from $12/month without a watermark. Prefer to run it yourself? Self-host free on GitHub.

what openshorts is

OpenShorts is an open source AI clip generator that turns long videos (podcasts, webinars, livestreams, interviews) into vertical 9:16 clips for TikTok, Instagram Reels and YouTube Shorts.

faster-whisper transcribes the video with word-level timestamps, PySceneDetect finds the scene boundaries, and Google Gemini 3.0 Flash scores the transcript to pick the 3 to 15 strongest moments of 15 to 60 seconds each. Each moment is then cut with FFmpeg and reframed to 9:16 with MediaPipe face tracking.

what it costs

OpenShorts self-hosted · $0

Free and open source under MIT. You run it with Docker on your own machine and bring your own API keys. No watermark, no usage cap, no subscription. What it costs you is hardware and time: on a typical CPU an 8-minute video takes 5 to 8 minutes to process.

OpenShorts Cloud · free tier, then from $12/month

The same software with the compute and API keys covered. An NVIDIA GPU clips that same 8-minute video in about 50 seconds. Free plan is 20 minutes a month with a watermark and no credit card. Paid plans start at $12/month for 100 minutes with no watermark, up to $59/month.

features

AI viral moment detection

Google Gemini 3.0 Flash scores the transcript and scene data to find the 3 to 15 strongest moments, so there is no manual scrubbing.

Smart 9:16 vertical cropping

Dual-mode reframing with MediaPipe face tracking and a YOLOv8 fallback, stabilised so the camera holds still instead of swinging.

Word-level automatic subtitles

faster-whisper produces a timestamp for every word, and the subtitles are burned in with FFmpeg.

AI voice dubbing in 30+ languages

ElevenLabs translates the audio while preserving the speaker's voice, then the new track is re-transcribed so subtitles match.

Hook text overlays

AI-written hook titles covering the first seconds, which is where a short-form viewer decides whether to stay.

AI video effects

Gemini-generated FFmpeg filter chains for colour grading, transitions and visual clean-up.

Local video upload

Podcasts, webinars, livestreams, interviews and vlogs, at full resolution, from a file or a YouTube link.

Self-hosted and private

Run it with Docker on your own machine and the source video never leaves your infrastructure.

Free AI YouTube studio

AI thumbnail generator, 10 viral title suggestions and auto-written descriptions with chapter timestamps.

Direct social publishing

Post to TikTok, Instagram Reels and YouTube Shorts from the dashboard.

AI UGC video generator

The AI writes a script and generates a lip-synced avatar video for any product or business, from $0.65 per video.

AI actors with lip-sync

Pick an AI actor or upload a photo to get a talking-head video with matched lip movement.

how it works

  1. Upload a long-form video. Any video you own: podcasts, webinars, livestreams, interviews, or a YouTube link.
  2. AI finds the best moments. Gemini 3.0 Flash returns 3 to 15 candidate clips of 15 to 60 seconds each.
  3. Smart cropping to vertical 9:16. Face-tracked reframing keeps the subject centred without the camera swinging.
  4. Subtitles, hooks and effects. Word-level subtitles, an AI hook overlay, optional effects and dubbing into 30+ languages.
  5. Download or post directly. Export the clips or publish straight to TikTok, Instagram Reels and YouTube Shorts.

how it compares

Entry pricing checked 27 July 2026. OpenShorts is $0 self-hosted or $12/month hosted without a watermark. Submagic starts at $14/month, Opus Clip at $15/month, Vizard at $19.99/month and Klap at $29/month. OpenShorts is the only open source and self-hostable option of the five.

Opus Clip alternative · Klap alternative · Vizard alternative · Submagic alternative · Free AI clip generator · Open source video clipper · How it works

frequently asked questions

Is OpenShorts free? What is the catch?
Both, and the distinction matters. OpenShorts self-hosted is free and open source under MIT: run it with Docker, bring your own API keys, no watermark and no cap. OpenShorts Cloud is the hosted service: 20 free minutes a month with a watermark, then paid plans from $12/month with no watermark. Self-hosted costs you hardware and time: on a typical CPU an 8-minute video takes 5 to 8 minutes to process, and you supply your own Google Gemini key, whose free tier covers 1,500 requests a day. On OpenShorts Cloud an NVIDIA GPU clips that same video in about 50 seconds, the Gemini key is included, auto-posting to TikTok, Instagram and YouTube is already wired up, and your clips stay retrievable from any browser.
What is OpenShorts and how does it work?
OpenShorts is an open source AI clip generator that turns long videos (podcasts, webinars, livestreams, interviews) into vertical 9:16 clips for TikTok, Instagram Reels and YouTube Shorts. faster-whisper transcribes the video with word-level timestamps, PySceneDetect finds the scene boundaries, and Google Gemini 3.0 Flash scores the transcript to pick the 3 to 15 strongest moments of 15 to 60 seconds each. Each moment is then cut with FFmpeg and reframed to 9:16 with MediaPipe face tracking.
How does OpenShorts compare to Opus Clip?
Both do AI viral moment detection and smart vertical cropping. OpenShorts is MIT-licensed and can be self-hosted, so the source video never leaves your machine, and it adds voice dubbing into 30+ languages plus an AI UGC generator with lip-synced actors. Opus Clip is closed source and cloud only, starting at $15/month as of July 2026, and it ships a larger caption-style library. Full comparison at /alternatives/opus-clip.
How does the smart vertical cropping work?
TRACK mode follows a single subject with MediaPipe face detection and a YOLOv8 fallback, damped so the crop holds still inside a safe zone rather than chasing every head movement. GENERAL mode handles group shots and landscapes by preserving the full width over a blurred backdrop. A speaker tracker prevents the crop from flipping between people and holds position through brief occlusions.
Can OpenShorts translate and dub videos?
Yes, into more than 30 languages through ElevenLabs, preserving the original speaker's voice characteristics. After dubbing, the audio is re-transcribed so the burned-in subtitles are in the target language rather than the original.
What is the AI UGC video generator?
It generates marketing videos with AI actors for any product or business. You describe the business or paste a website URL, and the AI writes a script, generates a lip-synced actor with voiceover, adds b-roll, subtitles and a hook overlay. Low Cost mode is about $0.65 per video and Premium is about $2.00. It works for restaurants, e-commerce, coaching, local businesses and apps, not only software.
What are the system requirements to self-host?
Any machine with Docker, realistically 8GB of RAM and a modern multi-core CPU. An NVIDIA GPU is optional and cuts processing time by roughly an order of magnitude. Docker Compose pulls Python 3.11, FFmpeg, YOLOv8, MediaPipe, faster-whisper and the React dashboard. Linux, macOS and Windows via WSL2 are supported.