Open-source Captions alternatives

Buzz is a desktop application that turns recorded speech into text and translates it, all on the user's own computer. It builds on OpenAI's Whisper speech recognition models, so audio files do not have to be uploaded to a third-party transcription service. The project is written in Python and released under the MIT license.

The app is distributed for Windows, macOS and Linux. Windows users get an installer, Linux users can choose Flatpak, Snap or AppImage packages, and a PyPI package exists for people who prefer a pip-based setup with ffmpeg installed. Nvidia GPU acceleration through CUDA is supported for faster transcription, and recent releases require Apple silicon on Macs.

Because processing happens locally, Buzz suits people who handle sensitive recordings or want to avoid per-minute fees from cloud transcription services. It runs as a local program rather than a hosted service, so there is no account to create.

Short Video Factory is an open-source desktop application that simplifies short video production with AI. You supply a text prompt together with storyboard footage, and the app generates copy, voiceover, edits and subtitles to produce marketing and general-interest clips with little manual work.

According to its README, the toolchain covers AI-driven script writing from prompts, text-to-speech narration, automated clip editing across common video formats, automatic subtitles and visual effects, and batch processing so multiple tasks can run in sequence from presets. It is a cross-platform desktop program for Windows, macOS and Linux, aimed at an out-of-the-box experience, and its topics reference TikTok-style short video content.

The project is written in TypeScript and licensed under AGPL-3.0. Its documentation is mainly in Chinese, with an English summary in the repository tagline. It suits marketers, small businesses and content creators who need to produce many short product or promotional videos quickly on their own computer.

AI YouTube Shorts Generator is an open-source alternative to clipping services such as Opus Clip, Vidyo.ai, Klap and SubMagic. You give it a long-form YouTube video and it returns ranked, vertical 9:16 clips suitable for Shorts, Reels and TikTok, without per-clip credits or watermarks.

Under the hood it transcribes the video with Whisper, uses a GPT-class language model to detect the most compelling moments, and crops the footage to a vertical frame automatically. The authors emphasize control over the highlight algorithm, and the repository topics cover auto-clipping, auto-cropping and highlight detection. It is written in Python.

The project is MIT-licensed and runs on your own machine with your own model access, which suits creators, agencies and developers who do not want subscription fees or minute caps. The website is run by a related commercial video tool, so check for a hosted option there.