Turn long videos into viral vertical shorts and publish them to TikTok, Instagram and YouTube.
This MCP server (slug: io-github-mutonby-openshorts, name: io.github.mutonby/openshorts) is described as a system to turn long videos into viral vertical shorts and publish them to TikTok, Instagram, and YouTube. The repository is associated with video clipping and generation capabilities, including AI clip generation.
🛠️ Key Features
Video short generation (“shorts” / “clip-generator”)
Two people on camera? OpenShorts stacks them instead of shrinking the wide shot, puts the captions on the seam where they cover nobody, and switches back to a face-tracked crop when the cut goes to one person. The AI picks the layout per video; nothing to configure.
Cloud version: don't want to run it yourself? OpenShorts Cloud is the same software on a GPU. Free plan: your first video is clipped whole up to 60 minutes, then 20 minutes a month, with a watermark and no credit card. Paid plans from $12/mo remove the watermark and add auto-posting and Autopilot (below).
Self-hosting is genuinely free and always will be. It costs you a machine, your own API keys and the time to keep it running. The hosted plans exist to cover that hardware and those keys.
Compared to Opus Clip, Klap, Vizard (public pricing pages, checked October 2026; full breakdown at openshorts.app/alternatives):
Free plan
Paid from
Open source
OpenShorts
Self-hosted: free, no watermark, no cap. Cloud: first video up to 60 min, then 20 min/mo, watermarked
$12/mo (Cloud, 100 min)
Yes, MIT
Opus Clip
60 min/mo, watermarked, export within 3 days
$15/mo (Starter, 150 min), billed per minute of source
No
Klap
1 video to try, no ongoing free plan
$14/mo billed yearly (100 clips), billed per clip
No
Vizard
60 min/mo, 720p, watermarked
$14.50/mo billed yearly ($29 monthly), billed per minute uploaded
Paste a YouTube link or upload a file. OpenShorts finds the strongest moments of a podcast, webinar, stream or interview and returns finished 9:16 clips: reframed, captioned, with a hook line, a virality score and titles for each platform.
A clip with its viral score, titles and edit actions
Every clip opens in a real editor: source and program monitors side by side with the full transcript. Click a word to set a cut, add segments, change the framing and re-render in seconds.
The clip editor with source monitor, program monitor, transcript and segments
2. Autopilot (Cloud)
Connect your YouTube channel and publish as usual. Every new video is clipped on its own, you get an email when the clips are ready, and with autopublish on the best ones go out to your socials (TikTok, Instagram, YouTube, Facebook, LinkedIn, Threads and Bluesky), one a day at the hour you pick. Paid plans only.
Autopilot settings
3. AI Shorts (UGC Video Creator)
Generate marketing videos with AI actors for any product or business. No camera, no studio, no influencer budget. Describe your product or paste a URL.
The UGC gallery with AI actor videos
Two cost modes: Low Cost ($0.65/video) and Premium ($2/video)
AI actors with lip-sync, voiceover, b-roll and TikTok-style subtitles
Pick an avatar from the shared gallery or upload your own photo
AI titles (10 options with a refinement chat), thumbnails with your face over a background, descriptions with chapter timestamps, and one-click publishing to YouTube.
5. Inside Claude and ChatGPT
Add OpenShorts to Claude or ChatGPT with one URL and ask for clips in plain language: same pipeline, same minutes, no API key to manage. See Automate it.
Connecting OpenShorts to an AI agent
Key Features
Clip Generator
Viral Moment Detection: Google Gemini 3.1 Flash-Lite ranks the transcript and scene boundaries to pick 3-15 moments of 15-60 seconds, each with a virality score
Runs fully local if you want: point LLM_BASE_URL at Ollama, LM Studio, vLLM or any OpenAI-compatible server and the moment picker runs on your own model, no Google key needed (see Run without a Google key)
Smart 9:16 Reframing: per scene: TRACK (MediaPipe + YOLOv8 face tracking), GENERAL (blurred background), SPLIT (two speakers stacked, captions on the seam) and SCREENCAST (screen over presenter); the layout is picked per video by Gemini or forced from the dashboard
Captions: faster-whisper (or Parakeet on GPU) with word-level timestamps, several caption styles, burned into the clip
Clip editor: word-level cuts, extra segments, framing changes and fast re-renders
Hook overlays: an opening line written from what is said in the clip, editable in text, style, font and position
AI Voice Dubbing: ElevenLabs, 30+ languages with voice cloning (bring your own ElevenLabs key, on the Cloud too)
Post a clip to TikTok, Instagram, YouTube, Facebook, LinkedIn, Threads and Bluesky at once, or schedule it for any date and time
Schedule a week: spread a batch of clips across the coming days in one go
Post analytics: views of the clips you published from OpenShorts, in the app
On the Cloud it is wired up on every paid plan; self-hosted, paste your own Upload-Post key
Only want to post videos you already have, without clipping? Use Upload-Post directly: TikTok, Instagram, YouTube, LinkedIn, Facebook, X, Threads, Pinterest, Bluesky and more, with a free plan, a REST API and an MCP server
AI Shorts Pipeline
Analyze: Scrape website URL + web research, or generate from manual description
Script: AI writes viral scripts (hook - problem - solution - CTA format)
Actor: Generate AI actors with Flux 2 Pro or select from shared gallery
Self-hosting OpenShorts is free. You provide the machine and you only pay for the AI APIs you use, and most have generous free tiers:
Service
Free Tier
Paid Cost
Used For
Google Gemini
Free trial with generous limits
< $0.01 per 10-min video
Viral moment detection, script generation, web research
Local LLM (Ollama, LM Studio, vLLM...)
Free, your hardware
$0
Viral moment detection instead of Gemini (LLM_BASE_URL)
fal.ai
Pay-per-use
~$0.50-1.50 per AI Short
Actor generation, talking head video, lip-sync
ElevenLabs
Free tier available
Pay-per-use
Voiceover, voice dubbing
Upload-Post
10 free uploads/month to all networks (no credit card)
Pay-per-use
Auto-publishing to TikTok, Instagram, YouTube
AWS S3
Optional
~$0.023/GB
Cloud backup for clips and gallery
Bottom line: You can clip videos for practically free with Gemini, and publish 10 videos/month to all social networks at zero cost with Upload-Post.
Don't want to run any of that?openshorts.app is the same software on our hardware: our NVIDIA GPU clips an 8-minute video in about 50 seconds instead of the 5 to 8 minutes it takes on a typical CPU, the Gemini key is included, and paid plans add auto-posting and Autopilot with nothing to set up. The free plan clips your first video whole up to 60 minutes, then 20 minutes a month, with a watermark and no credit card; paid plans start at $12/mo for 100 minutes without watermark.
Requirements
Docker & Docker Compose
Google Gemini API Key (Free — get it here) — required for all AI features
fal.ai API Key (Pay-per-use) — required for AI Shorts (actor generation, video, lip-sync)
ElevenLabs API Key (Free tier) — required for voiceover/dubbing
Upload-Post API Key (free tier) — required for direct social posting
Getting Started
1. Clone
bash
git clone https://github.com/mutonby/openshorts.git
cd openshorts
2. Configure (optional)
bash
cp .env.example .env# Edit .env with your AWS keys for S3 backup
3. Launch
bash
docker compose up --build
4. Open Dashboard
Navigate to http://localhost:5175
Go to Settings and enter your API keys (Gemini, fal.ai, ElevenLabs, Upload-Post)
Clip Generator: Upload a long-form video to generate viral shorts
AI Shorts: Describe your product or paste a URL to generate UGC marketing videos
YouTube Studio: Generate thumbnails, titles, and descriptions for YouTube
UGC Gallery: Browse all generated videos and avatars
AI Agent: Drop vertical videos in a folder and an agent skill picks, edits and queues clips for your approval
5. GPU acceleration (optional, NVIDIA)
The default image is CPU-only. With an NVIDIA card (any card with NVENC, e.g. RTX 4060) an 8-minute video clips in about a minute instead of 5 to 8. Nothing is passed through in the VM sense — the container just gets access to the host GPU.
sudo nvidia-ctk runtime configure --runtime=docker && sudo systemctl restart docker
docker run --rm --gpus all nvidia/cuda:12.4.0-base-ubuntu22.04 nvidia-smi # sanity check
On Windows use Docker Desktop with the WSL2 backend and the Windows NVIDIA driver; no driver inside WSL.
Compose: create docker-compose.override.yml next to docker-compose.yml (picked up automatically). GPU: "1" adds cuBLAS/cuDNN and onnxruntime-gpu to the image (~2 GB); video is required for NVENC.
WHISPER_MODEL=large-v3-turbo
WHISPER_DEVICE=cuda
WHISPER_COMPUTE=float16
FFMPEG_ENCODER=auto # probes h264_nvenc at startup, falls back to x264
TRANSCRIBE_BACKEND=parakeet # optional: ~2x faster than whisper, 25 European languages, auto-falls back to whisper
ASR_GPU_CONCURRENCY=1
The backend log on the first job reports the chosen encoder and transcription device. A CUDA error in whisper (e.g. VRAM exhausted) retries once on CPU automatically. 8 GB of VRAM is enough for large-v3-turbo fp16 plus the detection models.
6. Run without a Google key (local LLM, optional)
The only cloud call in the clip pipeline is the moment picker: it sends the
transcript (never the video) to Gemini. Point it at any OpenAI-compatible
server instead and the whole pipeline stays on your box:
bash
# .env
LLM_BASE_URL=http://host.docker.internal:11434/v1 # Ollama on the host
LLM_MODEL=qwen2.5:14b # any chat model that follows instructions# LLM_API_KEY=... # only if your server checks one (vLLM --api-key, OpenRouter)
Works with Ollama, LM Studio, vLLM, llama.cpp server, LocalAI and OpenRouter.
The dashboard stops asking for a Gemini key when this is set. Two things to
know:
Context length. A scoring call carries three transcript windows
(~2-3k tokens) and the detail call up to ten (~5k on a long podcast).
Ollama defaults to a 4096-token context and truncates silently, so run it
with OLLAMA_CONTEXT_LENGTH=16384 (or set num_ctx in a Modelfile); raise
LLM_SCORE_BATCH above 3 only if your context allows it. 7-8B models
return valid JSON reliably, 3B ones do not.
What still needs Gemini. Anything that has to look at frames: the
automatic layout picker (AUTO_LAYOUT), the on-screen content detector
and silent videos (no speech to clip by). Without a Gemini key those fall
back to the plain face-tracking crop, and a silent video fails with a
message that says so. Add a key alongside LLM_BASE_URL and you get both.
Technical Pipeline
Clip Generator
Ingest — YouTube URL (yt-dlp) or local upload
Transcribe — faster-whisper (or Parakeet on GPU) with word-level timestamps
Reframe — AI vertical cropping with subject tracking
Effects — Subtitles, hooks, AI video effects
Publish — S3 backup + Upload-Post social distribution
AI Shorts
Analyze — Website scraping + Gemini web research (or manual description)
Script — Gemini generates viral scripts with segments
Actor — Flux 2 Pro portrait generation (or gallery/upload)
Voice — ElevenLabs TTS voiceover
Video — Hailuo 2.3 Fast img2video + VEED Lipsync (Low Cost) or Kling Avatar v2 (Premium)
B-roll — Flux 2 Pro image generation + Ken Burns effect
Composite — FFmpeg assembly with ASS subtitles and hook overlays
Gallery — Upload to public S3 with metadata for SEO pages
Publish — Upload-Post to TikTok, Instagram, YouTube
Automate It: MCP Server, REST API and Webhooks
You don't need the dashboard. The whole pipeline is callable by AI agents and scripts.
MCP server (/mcp)
OpenShorts ships a built-in MCP server, so Claude, ChatGPT, Cursor or any MCP client can clip and publish videos for you:
claude.ai and ChatGPT: paste https://mcp.openshorts.app/mcp as a custom connector (Settings → Connectors) and approve the access on openshorts.app. The server does OAuth 2.1 with dynamic client registration, so there is no key to copy; the connection shows up under Account → API keys, where revoking it disconnects the app.
bash
# Claude Code / Cursor / n8n (hosted): create an API key in your account page
claude mcp add --transport http openshorts https://mcp.openshorts.app/mcp \
--header "Authorization: Bearer osk_..."# Self-hosted (no key needed, BYOK rules apply):
claude mcp add --transport http openshorts http://localhost:8000/mcp
# Self-hosted without running the web server: same tools over stdio
claude mcp add openshorts -- python mcp_stdio.py
Tools: process_video (URL or upload_id; captions: false when the source already has subtitles, auto_hook: false to skip the hook line, burned by default like the dashboard), create_upload (hand the agent a local file: PUT the bytes, then process), get_job_status, list_clips, get_quota, add_subtitles, recut_clip, publish_clip. A prompt like "clip this podcast and schedule the best 3 to TikTok" is now a one-liner in your agent of choice.
REST API + API keys
Hosted accounts can mint osk_... API keys (account page). A key authenticates as you everywhere — same plan, same minutes, same job ownership:
Interactive docs at /docs (OpenAPI) on any instance.
Completion webhooks
Pass webhook_url (and optionally webhook_secret) to POST /api/process and you get exactly one POST when the job reaches a terminal state — no polling loops in your n8n / Zapier / cron pipelines:
skills/openshorts/SKILL.md follows the open
Agent Skills standard, so it works in any
skill-capable agent:
bash
# Claude Code (and most agents): copy the folder into the skills directorycp -r skills/openshorts ~/.claude/skills/
# Hermes Agent: install straight from this repo
hermes skills install mutonby/openshorts/skills/openshorts
# OpenClaw: from ClawHub
openclaw skills install @mutonby/openshorts
n8n
An importable workflow (video URL in, published-ready clips out, no polling)
lives in examples/n8n/.
On OpenShorts Cloud none of this is needed: paid plans connect your socials from the app.
Star History
Contributions
Contributions are welcome! Whether it's adding new AI models, improving the lip-sync pipeline, or building new features — feel free to open a PR.
License
MIT License for the core application — OpenShorts is yours to use, modify, and scale.
Exception: the cloud/ directory (billing, managed keys, and the hosted-service infrastructure behind the optional BILLING_ENABLED flag) is source-available under the OpenShorts Commercial License. You can read it, modify it, and self-host it for personal or internal use, but you can't offer it to third parties as a paid/hosted service. Self-hosting the core app never requires this directory.
Install
Remote endpoint
Streamable HTTP
Hosted server - connect over the network, no local install.