mutonby/openshorts

★ 7,627⑂ 1,645

Open source AI clip generator: turns long videos into viral 9:16 shorts with AI moment detection, face tracking, subtitles and dubbing.

About mutonby/openshorts

mutonby/openshorts is an open-source project on GitHub, mainly written in Python. Open source AI clip generator: turns long videos into viral 9:16 shorts with AI moment detection, face tracking, subtitles and dubbing. It currently holds 7,627 stars and 1,645 forks with 11 open issues, and was last pushed on 2026-11-10 (repository created 2025-12-19).

Project Overview

Git Homed tracks it on the Video Trending board and on the AI Video Trending list.

GitHub Repository Details

Repository mutonby/openshorts · default branch main · size 101795 KB · watchers 55 · source: GitHub REST API and repository README

README

OpenShorts.app

The open-source OpusClip alternative. Turn long videos into viral 9:16 Shorts, TikToks and Reels. Self-host free (MIT) or use the hosted cloud.

| | OpenShorts | OpusClip | Vizard | Klap | |---|---|---|---|---| | Open source | Yes (MIT) | No | No | No | | Self-hostable | Yes (Docker) | No | No | No | | Free without watermark | Yes, self-hosted | No | No | No | | API + MCP server | Yes | API | API | API |

License: MIT Open Source PRs Welcome Docker GitHub stars Last Commit

Open source AI video platform with 3 tools in one: Clip Generator, AI Shorts (UGC videos with AI actors), and YouTube Studio.

Your podcast, and the vertical clip OpenShorts makes of it: both speakers stacked, captions on the seam

Real OpenShorts output, not a mock-up. Source: Turn the Tables with Dan and Shoshana Jordan, Heritage of Faith, licensed CC BY.

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).

Two ways to run it, same software either way:

| | Self-hosted (this repo) | Hosted on openshorts.app | |---|---|---| | Price | Free forever, MIT | Free plan, paid from $12/mo | | Speed | 5 to 8 min per 8-min video on CPU | About 50s on our NVIDIA GPU | | API keys | Bring your own Gemini, ElevenLabs, fal.ai | Gemini included, nothing to set up | | Watermark / limits | None, ever | Watermark and 20 min/mo on the free plan, neither on paid | | Auto-posting | With your own Upload-Post account | Paid plans: connect TikTok, Instagram, YouTube, Facebook, LinkedIn, Threads and Bluesky once, post or schedule from the app | | Autopilot | Not included | Paid plans: every new video on your channel becomes scheduled shorts | | Setup | Docker, 8GB+ RAM, model downloads | Sign in and paste a link | | MCP / API for agents | Same /mcp endpoint, but only while your machine is on | Always-on endpoint at mcp.openshorts.app, API keys in one click | | Your data | Your server | Ours |

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 | No |

Video: the story behind OpenShorts Cloud

[Launching the paid plan of an open source app](https://www.youtube.com/watch?v=Bf5z-Wh9QxM "Watch on YouTube")

In Spanish. Click the image to watch on YouTube.

---

What's Inside

1. Clip Generator

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

4. YouTube Studio

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

Social Auto-Publishing (via Upload-Post)

AI Shorts Pipeline

1. Analyze: Scrape website URL + web research, or generate from manual description 2. Script: AI writes viral scripts (hook - problem - solution - CTA format) 3. Actor: Generate AI actors with Flux 2 Pro or select from shared gallery 4. Voice: ElevenLabs TTS voiceover (English/Spanish, male/female) 5. Video: Talking head generation (Hailuo 2.3 Fast img2video + VEED Lipsync, or Kling Avatar v2 in Premium) 6. B-roll: AI-generated visuals with Ken Burns effect 7. Composite: FFmpeg final assembly with subtitles and hook overlays 8. Publish: Direct posting to TikTok, Instagram Reels, YouTube Shorts via Upload-Post

Infrastructure

---

Who Is This For?

---

AI Shorts Showcase

Videos generated with OpenShorts AI Shorts — no camera, no studio, no actors:

| | | | |:---:|:---:|:---:| | Biohacking for Investors | Secret Weapon for Devs | El Secreto de los Agentes de IA | | Biohacking for Investors · LOW COST | Secret Weapon for Devs · LOW COST | El Secreto de los Agentes de IA · PREMIUM |

Browse all videos at openshorts.app/gallery

---

OpenShorts vs Competitors

| Feature | OpenShorts | Opus Clip | CapCut | Vizard | Klap | Descript | |---------|:---:|:---:|:---:|:---:|:---:|:---:| | Price | Free self-hosted
from $12/mo hosted | $15-29/mo | $8/mo | $14.50/mo yearly
$29 monthly | from $14/mo yearly | $24-65/mo | | Self-hosted | Yes | No | No | No | No | No | | Open source | Yes | No | No | No | No | No | | Watermark | Never self-hosted
free plan only when hosted | Free tier | Some | Free tier | No free plan
(1 trial video) | Free tier | | Upload limits | None self-hosted
by plan when hosted | 10-30GB | Credit-based | 60min-10hr | 10-100 vids/mo | 60min-40hr | | AI clip detection | Yes | Yes | Yes | Yes | Yes | Yes | | Smart 9:16 reframing | Yes | Yes | Yes | Yes | Yes | No | | Auto subtitles | Yes | Yes | Yes | Yes | Yes | Yes | | Voice dubbing (30+ langs) | Yes, with your ElevenLabs key | No | Pro only | No | Pro only | Business only | | AI UGC actors | Yes | No | No | No | No | No | | AI video effects | Yes | No | Yes | No | No | No | | Hook text overlays | Yes | No | No | No | No | No | | YouTube Studio (titles, thumbnails) | Yes | No | No | No | No | No | | Social auto-publishing | Yes | Pro only | TikTok only | Paid only | Paid only | No | | Schedule uploads | Yes | Pro only | No | Paid only | Paid only | No | | Data privacy | Your server | Their cloud | Their cloud | Their cloud | Their cloud | Their cloud | | Works with a local LLM (Ollama) | Yes | No | No | No | No | No |

---

How Much Does It Cost?

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

---

Getting Started

1. Clone

git clone https://github.com/mutonby/openshorts.git
cd openshorts

2. Configure (optional)

cp .env.example .env

Edit .env with your AWS keys for S3 backup

3. Launch

docker compose up --build

4. Open Dashboard

Navigate to http://localhost:5175

1. Go to Settings and enter your API keys (Gemini, fal.ai, ElevenLabs, Upload-Post) 2. Clip Generator: Upload a long-form video to generate viral shorts 3. AI Shorts: Describe your product or paste a URL to generate UGC marketing videos 4. YouTube Studio: Generate thumbnails, titles, and descriptions for YouTube 5. UGC Gallery: Browse all generated videos and avatars 6. 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.

Host: install the NVIDIA driver (nvidia-smi must work) and the NVIDIA Container Toolkit:

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.

services:
  backend:
    build:
      context: .
      args:
        GPU: "1"
    deploy:
      resources:
        reservations:
          devices:
  • driver: nvidia
count: all capabilities: [gpu, video]

.env:

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

Verify:

docker compose up --build -d
docker exec openshorts-backend nvidia-smi -L
docker exec openshorts-backend ffmpeg -hide_banner -f lavfi -i testsrc=size=256x256:rate=1 -frames:v 1 -c:v h264_nvenc -f null -
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:

# .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:

(~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. 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

1. Ingest — YouTube URL (yt-dlp) or local upload 2. Transcribe — faster-whisper (or Parakeet on GPU) with word-level timestamps 3. Detect — PySceneDetect for scene boundaries 4. Analyze — Gemini identifies 3-15 viral moments (15-60s each) 5. Extract — FFmpeg precise clip cutting 6. Reframe — AI vertical cropping with subject tracking 7. Effects — Subtitles, hooks, AI video effects 8. Publish — S3 backup + Upload-Post social distribution

AI Shorts

1. Analyze — Website scraping + Gemini web research (or manual description) 2. Script — Gemini generates viral scripts with segments 3. Actor — Flux 2 Pro portrait generation (or gallery/upload) 4. Voice — ElevenLabs TTS voiceover 5. Video — Hailuo 2.3 Fast img2video + VEED Lipsync (Low Cost) or Kling Avatar v2 (Premium) 6. B-roll — Flux 2 Pro image generation + Ken Burns effect 7. Composite — FFmpeg assembly with ASS subtitles and hook overlays 8. Gallery — Upload to public S3 with metadata for SEO pages 9. 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.

# 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:

curl -X POST https://api.openshorts.app/api/process \
  -H "Authorization: Bearer osk_..." -H "Content-Type: application/json" \
  -d '{"url": "https://youtube.com/watch?v=...", "acknowledged": true,
       "webhook_url": "https://your-server.com/hooks/openshorts"}'

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:

{"event": "job.completed", "job_id": "…",
 "clips": [{"index": 0, "title": "…", "video_url": "…", "download_url": "…"}]}

With a secret, the body is signed: X-OpenShorts-Signature: sha256=.

CLI

The same API from the terminal, zero dependencies (cli/):

pip install openshorts   # or: uvx openshorts

export OPENSHORTS_API_KEY=osk_... # hosted

export OPENSHORTS_API_URL=http://localhost:8000 # self-hosted, no key

openshorts process "https://youtube.com/watch?v=..." --wait openshorts clips <job_id> openshorts publish <job_id> 0 --platforms tiktok,youtube

Agent skill

skills/openshorts/SKILL.md follows the open Agent Skills standard, so it works in any skill-capable agent:

# Claude Code (and most agents): copy the folder into the skills directory
cp -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/.

---

Tech Stack

| Layer | Technology | |-------|-----------| | Backend | Python 3.11, FastAPI, google-genai, faster-whisper, ultralytics (YOLOv8), m

GitHub Stars & Activity

7,627Stars
1,645Forks
11Open issues
PythonLanguage

GitHub Popularity

GitHub stars7,627
Forks1,645
Open issues11
Primary languagePython
LicenseMIT
Stars gained today0
Created2025-12-19
Last pushed2026-11-10

Trending History

Trending statusnot on today's boards

Related GitHub Projects

1

harry0703 / MoneyPrinterTurbo

Python★ 144,122⑂ 0
→
2

OpenMontageInc / OpenMontage

Python★ 81,161⑂ 0
→
3

ATH-MaaS / Pixelle-Video

Python★ 30,170⑂ 0
→
4

Wan-Video / Wan2.2

Python★ 18,718⑂ 0
→
5

Zulko / moviepy

Python★ 15,157⑂ 0
→
6

zai-org / CogVideo

Python★ 13,207⑂ 0
→
7

HKUDS / ViMax

Python★ 12,943⑂ 0
→
8

Tencent-Hunyuan / HunyuanVideo

Python★ 12,785⑂ 0
→

More Trending Repositories