Drop in a podcast or interview, get captioned vertical clips. No account, no API key, no upload. Free and open source (MIT): no watermark, no credits, no subscription. Runs on your own PC.
A real run: the 9:16 crop cuts to whoever is talking, with word-timed captions.
| 🪟 Windows, no setup | ⬇ ShortsFlow-Setup.exe, open ShortsFlow, press Try a 2-minute sample, then Start. |
| 🍎🐧 Mac or Linux | curl -fsSL https://raw.githubusercontent.com/ghost1412/shortsflow/main/install.sh | sh (needs Python 3.10+ and FFmpeg; installs into ~/.shortsflow). |
| 💻 Any OS | pip install "shortsflow[clip]", then shortsflow doctor, then shortsflow clip my_video.mp4 |
| ☁️ Nothing to install | Open in Colab (free GPU) |
If it saves you a subscription, a ⭐ on this repo helps other people find it.
No account or API key is needed to clip a video. A key (or a free local Ollama) adds AI-written titles and descriptions and lets the AI pick and score the moments (a cloud provider then receives the transcript text).
The browser app after a run on a public-domain NASA video: each short has a score, the reason it was picked and an editor. Tick "Let me review the moments first" to check the picks before anything is rendered.
- The moments. Local Whisper reads the speech; clips start and end on sentences, skip a mic check or a mumbled opening, and never overlap. Every clip says why it was picked.
- The framing. Face-tracked 9:16 crops, a cut to whoever is speaking in a two-person talk, and the whole picture over a blurred copy for slides and screen recordings.
- The captions. Animated word-by-word captions (Hormozi, glow box, bounce), your logo and handle, and an editor to re-cut or restyle any clip.
- Tighter pacing.
--tightenremoves silences and pauses between words, never a spoken word, and keeps laughter and applause.
Six of the 14 caption styles. Pick one in the app or with --caption_style.
# the one command most people need
shortsflow clip interview.mp4 --captions
# a podcast: cut to whoever is talking, remove silences, animated captions
python main.py --source_video "https://www.youtube.com/watch?v=VIDEO_ID" --extract_mode shorts \
--clip_count 3 --layout auto --smart_crop --tighten --use_remotion --caption_style HORMOZIClip quality is checked on public-domain and Creative Commons videos with no AI key at all, with a benchmark that runs on GitHub's runners
(python scripts/clip_benchmark.py <session> --picture): clips that start and end on a sentence, no overlap, length near the asked one,
a standalone opening line, titles that say only what the clip says, a face found and centred. The workflow is .github/workflows/clip_benchmark.yml. The results table, including the weak spots, is in docs/BENCHMARKS.md. We do not claim to beat Opus Clip on every video; a side-by-side on public footage is the next thing to publish.
| ShortsFlow | Opus Clip, Klap, Vizard | |
|---|---|---|
| Price | Free, MIT | Subscription or credits |
| Watermark | None | On the free tier |
| Where your video goes | Stays on your machine; Whisper runs locally (text goes to an AI provider only if you add a key) | Uploaded to their cloud |
| Account | Not needed | Required |
| Best at | Podcasts and interviews, privacy, full control | Polish, hosted convenience |
Everything runs locally by default. Only these leave it, and each is optional: AI text providers (Gemini, Groq, Hugging Face, Ollama is local) receive the
transcript text when you set a key; Gemini receives small frames for --visual_context when a key is set; OpenStreetMap place names for trip recaps
(--recap_no_geocode turns it off); Microsoft's Edge voice service or ElevenLabs receive the text to speak in the dub and idea-to-video modes;
Google Drive upload only when you ask. A pasted YouTube link is downloaded to your PC; use your own files where the video's terms require it.
The transcript of each video you process is also kept on your PC in ~/.shortsflow/cache/transcripts so it is not redone; delete that folder's files or set SHORTSFLOW_TRANSCRIPT_CACHE=off to stop it. If you start the browser app for other devices (--host 0.0.0.0 or --share), visitors cannot use file paths or folder boxes; behind your own tunnel or reverse proxy, set SHORTSFLOW_REMOTE=1 yourself.
Browser app, desktop studio, CLI, Docker, REST API, an MCP server for AI agents, dubbing, trip and event recaps, photo reels, step-by-step videos, game moments, and 30+ idea-to-video formats. They are documented in docs/FEATURES.md (the full feature reference).
Idea-to-video: a short from one line of text, and a "spot the lie" facts short.
- Something wrong? Open an issue with the output of
shortsflow doctor --report(it prints no keys and no folder names). - Status, known issues and how to verify a change: ROADMAP.md. Tests:
python -m pytest(offline). - Sample footage in the demos is public domain or Creative Commons and credited where used.
MIT. Remotion (animated captions) has its own licence for companies above its size threshold; see remotion.dev/license.
