divyaprakash0426/autoshorts

Automatically generate viral-ready vertical short clips from long-form gameplay footage using AI-powered scene analysis, GPU-accelerated rendering, and optional AI voiceovers.

42
/ 100
Emerging

Leverages PyTorch + CUDA for GPU-accelerated scene detection, audio analysis via `torchaudio`, and NVENC hardware encoding, with fallbacks to CPU-based libx264 and heuristic scoring when APIs unavailable. Supports OpenAI/Google Gemini for semantic analysis or runs entirely local; integrates PyCaps for styled subtitle rendering and Qwen3-TTS 1.7B for multi-language voiceover generation with voice design from natural language prompts. Output adapts dynamically across 7 semantic types (action, funny, clutch, etc.) and 10+ caption styles including GenZ slang and narrative modes, with automatic voice persona matching per style.

137 stars.

No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 11 / 25
Community 11 / 25

How are scores calculated?

Stars

137

Forks

11

Language

Python

License

MIT

Last pushed

Feb 19, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/divyaprakash0426/autoshorts"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.