Turn a raw talking-head clip into a captioned, jump-cut vertical reel for Instagram, TikTok or YouTube Shorts. Any LLM plans the edit (Claude, OpenAI, Gemini, or a local model) and ffmpeg renders it.
raw 4-min phone clip ──► reelcut make clip.mp4 ──► 1:50 reel, 1080×1920
What you get, in the style of fast-cut creator reels:
- Jump cuts. Pauses, stutters, restarted sentences and walk-offs are removed.
- Punch-in zooms alternate on every cut, with a slow push-in on longer takes.
- Word-by-word captions. Bold text, 2–3 words at a time; the spoken word lights up yellow and keywords are green.
- A hook title over the first 2.5 seconds.
- Zoom-pop transitions with a pop sound wherever footage was skipped (for example, you left the frame to fetch something).
- A running counter gag (
TECH COUNT: 7,+1 MACBOOK) with a bell "ting" on every increment, when the video lists things. - Stamps for punchlines (
NOT A FLEX) and an outro with a comment prompt. - A colour grade (
vintage,punchy,clean), a vignette, and loudness normalised to −14 LUFS.
- Transcribe. faster-whisper runs locally and gives word-level timestamps. No API key is needed.
- Plan. The transcript, the silence map and contact sheets (a thumbnail every 2 s) go to the model you choose. It returns a JSON edit plan: cuts, corrected caption text, hook, keywords, counter events, stamps, outro and face position. The plan is validated (clamped, sorted, overlaps removed) and saved as
plan.json. - Render. ffmpeg cuts each segment, frames the face in 9:16, adds the zoom and pop effects, burns in the captions, mixes in the sound effects, applies the grade and normalises the loudness.
The model only writes a plan; it never touches the video. That makes the result reproducible and lets you fix the plan by hand.
You need Python 3.10+ and ffmpeg on your PATH.
pip install "reelcut[all] @ git+https://github.com/3liAf/reelcut"Or install only the SDK you'll use: reelcut[claude], reelcut[openai] or reelcut[gemini].
# Uses whichever key is set: ANTHROPIC_API_KEY, OPENAI_API_KEY, or GEMINI_API_KEY / GOOGLE_API_KEY
reelcut make clip.mp4
# Choose a provider and model explicitly
reelcut make clip.mp4 --provider claude
reelcut make clip.mp4 --provider openai --model gpt-5
reelcut make clip.mp4 --provider gemini --model gemini-2.5-pro
# A local model through any OpenAI-compatible server (LM Studio, Ollama, vLLM)
reelcut make clip.mp4 --provider openai --base-url http://localhost:1234/v1 --model qwen2.5-vl-7b
# add --no-images if the model can't read images
# No model at all: silence cutting and captions only
reelcut make clip.mp4 --provider nonereelcut plan clip.mp4 # writes clip.reelcut/plan.json
# edit the JSON: fix a caption, drop a cut, change the hook...
reelcut render clip.mp4 # renders clip.reelcut/plan.jsonRe-renders only redo the cuts you changed. See examples/plan.example.json for the format.
| flag | default | |
|---|---|---|
--provider |
auto |
auto, claude, openai, gemini or none |
--model |
per provider | also $REELCUT_MODEL |
--base-url |
custom or local endpoint | |
--grade |
vintage |
vintage, punchy, clean, none, or any ffmpeg filter chain |
--font |
Arial Black |
caption font; must be installed |
--pop-gap |
3.0 |
skipped seconds that trigger a zoom-pop |
--whisper-model |
small |
medium or large-v3 is more accurate but slower |
--language |
auto | e.g. en, de |
-o |
<clip>_reel.mp4 |
| provider | SDK | default model | notes |
|---|---|---|---|
claude |
anthropic |
claude-opus-5-5 |
structured JSON output; server-side refusal fallback is turned on |
openai |
openai |
gpt-5 |
Chat Completions with a strict JSON schema; also works with OpenAI-compatible servers |
gemini |
google-genai |
gemini-2.5-pro |
JSON mode; the schema is sent in the prompt and the reply is checked by reelcut |
Model names change often. If a default has been retired, pass --model. To add a provider, implement one complete_json(system, prompt, images, schema) -> dict method in reelcut/providers.py.
- Film vertically, with the camera at chest height and your face in the upper third.
- Pause for a beat between thoughts. Clean gaps make clean cuts.
- When you fetch something, leave the frame and come back. reelcut turns that into a pop transition.
pip install -e ".[all,dev]"
pytestThe tests cover plan validation, the timeline and captions, cropping, and provider selection. They need no network and no ffmpeg.
MIT