Drop in a long video — podcast, interview, talk, stream — and VibeClip cuts it into vertical, captioned, ready-to-post shorts. Then you refine every clip by chatting: “make clip 2 punchier,” “bigger captions,” “add a zoom at 0:05,” “undo.”

Quick start · Features · How it works · Bring your own key · Configuration · Contributing

_{Left: the raw clip. Right: after one sentence — “make it mrbeast style and add gameplay underneath” — captioned, reframed to 9:16, and split-screened. Real pipeline output, not a mockup.
Footage: Andy Dickinson (CC-BY) · gameplay: Orbital - No Copyright Gameplay (CC-BY) · Minecraft © Mojang.}

Spin up a private instance in three commands. All you add is one LLM key.

git clone https://github.com/oktaydbk54/vibeclip.git
cd vibeclip
cp .env.example .env          # add ONE line: OPENAI_API_KEY=sk-...
docker compose up -d --build
# → open http://localhost:8765

With the defaults (EMAIL_MODE=console, REQUIRE_EMAIL_VERIFICATION=false) sign-up logs you straight in — no email provider needed. Bring an OpenAI or DeepSeek key (DeepSeek is the cheap one), or point LLM_BASE_URL at any OpenAI-compatible server (Ollama, LM Studio, OpenRouter…). Prefer no Docker? See local install.

        upload
          │
   ┌──────▼───────┐   faster-whisper (local, no API key)
   │  transcribe  │
   └──────┬───────┘
   ┌──────▼────────────┐   LLM "brain" (your key) — structure + scored moments
   │ analyze structure │
   │  find highlights  │
   └──────┬────────────┘
   ┌──────▼───────┐   per clip, replayed from cached intermediates (~2–4s/edit)
   │  auto edit   │  jumpcut → 9:16 reframe → captions → music+ambience (ducked)
   │              │  → SFX → fades   ·   then your chat commands layer on top
   └──────┬───────┘
        export  →  vertical MP4, publish-ready

Only two things ever hit the network: your chosen LLM (to understand intent and score moments) and, optionally, Pexels (stock b-roll). Speech-to-text and all rendering stay on your machine.

VibeClip never ships with a key and never proxies your prompts anywhere except the provider you choose. Two ways to supply one:

• Per instance — set OPENAI_API_KEY (or DEEPSEEK_API_KEY, or any OpenAI-compatible endpoint via LLM_BASE_URL) in .env.
• Per user — each account pastes its own key on the in-app Settings page, with a live test-connection. Keys are encrypted at rest and never sent back to the browser.

Speech-to-text runs locally and needs no key.

Everything is driven by .env (see .env.example for the full, commented list). The ones that matter most:

Requirements: Python 3.12+, ffmpeg, and the DejaVu fonts (for caption rendering).

cp .env.example .env          # add your LLM key
uv sync                       # or: pip install -e .
python -m chat.app            # → http://127.0.0.1:8765

First run downloads the Whisper model. Prefer the terminal? python -m chat.cli <video.mp4>.

The repo bundles a small library of royalty-free media (music, ambience, SFX, demo footage) for the built-in styles. Some tracks are CC-BY (Kevin MacLeod) and require crediting in your video description — see the CREDITS files under assets/. VibeClip never bundles or uses copyrighted/branded game footage.

Issues and PRs welcome — start with CONTRIBUTING.md. Security reports: see SECURITY.md. Be excellent to each other (code of conduct).

GNU AGPL-3.0 — see LICENSE. You can self-host and modify VibeClip freely; if you run a modified version as a network service, you must offer that modified source to its users. Copyright © 2026 the VibeClip authors.