Turn a long podcast or interview recording into short vertical clips automatically.
Add word-synced burned-in captions to video clips without manual editing.
Refine a generated clip using chat commands like 'make it punchier' or 'bigger captions'.
Apply built-in style presets like hormozi or mrbeast to match a specific creator aesthetic.
| oktaydbk54/vibeclip | 13127905/deep-learning-based-air-gesture-text-recognition- | 6xvl/paralives-plugins-index | |
|---|---|---|---|
| Stars | 15 | 15 | 15 |
| Language | Python | Python | Python |
| Setup difficulty | moderate | moderate | easy |
| Complexity | 3/5 | 3/5 | 2/5 |
| Audience | general | developer | general |
Figures from each repo's GitHub metadata at analysis time.
Requires Docker and your own API key for an AI language model such as OpenAI, Gemini, or Claude.
VibeClip is a self-hosted video editing tool that takes long videos and automatically cuts them into short vertical clips suitable for platforms like TikTok, Instagram Reels, or YouTube Shorts. You upload a podcast, interview, or stream recording and the tool transcribes the speech, identifies the strongest moments, reformats the video to a 9:16 vertical layout, and burns in word-synced captions. You can then refine each clip by typing instructions in a chat box: "make clip 2 punchier," "bigger captions," "add a zoom at 0:05," "undo." The tool runs entirely on your own computer or server. Speech-to-text processing happens locally using an on-device model called faster-whisper, which means no audio is sent to any outside service. The only things that require a network connection are the AI language model you choose (which handles understanding your instructions and picking the best moments) and an optional stock video service called Pexels if you want background footage. You supply your own API key for whichever AI service you prefer: OpenAI, DeepSeek (described as the budget option), Google Gemini, Anthropic Claude, or a locally running model via Ollama or a compatible tool. Installation takes three commands using Docker. You clone the repository, copy an example settings file and add your API key, then run Docker to start the service. A web interface opens at a local address in your browser. You can also run it without Docker if you have Python and ffmpeg installed. The web interface includes a live preview of the vertical clip, a timeline editor, and the chat panel. Built-in style presets let you apply a specific look to a clip in one step: options include styles named hormozi, mrbeast, podcast_minimal, and kinetic, each applying a particular combination of caption style, pacing, zoom behavior, and music. You can also create your own preset as a JSON file. The project is open source under the AGPL-3.0 license, which means you can use and modify it freely, but if you run a modified version as a service for others, you must share the modified source code.
A self-hosted tool that turns long videos into short vertical clips with auto-captions for TikTok, Reels, and Shorts.
Mainly Python. The stack also includes Python, Docker, faster-whisper.
You can use and modify it freely, but if you run a modified version as a service for others, you must share the modified source code.
Setup difficulty is rated moderate, with roughly 30min to a first successful run.
Mainly general.
This repo across BitVibe Labs
Verify against the repo before relying on details.