An assembly line for short-form video, on your desktop

What it does Short Video Factory is a cross-platform desktop app built in TypeScript that ingests a text prompt plus raw video clips and spits out a finished short. It strings together AI-generated copy via an OpenAI-compatible API, synthetic speech through EdgeTTS, automated editing, and basic subtitles into a single pipeline. The target audience is product marketers and general creators who need polished short-form output without wrestling with a traditional NLE.

The interesting bit The tool treats video production like a factory line: batch processing is a first-class citizen, letting you queue presets and auto-generate videos back-to-back. By leaning on existing standards—OpenAI-format endpoints for text and EdgeTTS for voice—it avoids reinventing the wheel or trapping you in proprietary cloud silos.

Key highlights

• Runs fully offline and local; your footage and prompts never leave the machine.
• Batch mode supports continuous, preset-driven video synthesis.
• OpenAI-compatible API integration for copywriting generation.
• Cross-platform builds for Windows, macOS, and Linux.
• Multi-language support, including Chinese and English.

Caveats

• Subtitle effects and multiple styling options are still on the roadmap; current subtitle support is basic.
• Voice synthesis is limited to EdgeTTS for now, with more providers planned.
• Fine-grained parameter adjustment is listed as a future feature, so expect a somewhat opinionated workflow today.

Verdict A solid fit for marketers, indie sellers, or content farms that need volume without subscription bloat. Professional editors who want frame-level precision should probably keep their NLE.