modelscope/FunClip
Open-source video clipping tool that uses speech recognition and LLM-based AI to transcribe and automatically clip video segments.

Velocity · 7d
+5.2
★ / day
Trend
→steady
star history
FunClip is an automated video clipping tool that leverages Alibaba’s FunASR Paraformer speech recognition models to transcribe videos, enabling users to select text segments or speakers and generate corresponding video clips. It integrates LLM-based AI clipping for intelligent segment selection. The tool is deployed locally and provides a Gradio interface for easy use.