kvidai-video-use

Conversational video editing lets you describe cuts, pacing, and style in plain language. An AI agent then orchestrates transcription, silence-aware cutting, color grading, subtitle generation, and rendering to produce a polished final video without manual NLE operation.

Yes, automatic subtitle generation and transcription are supported. The Skill applies word-level transcription and silence-aware cutting using whisperx or kvidai STT, then burns subtitles directly into your final rendered video file.

Yes, ffmpeg and Python dependencies are required to run the video editing pipeline. Optional Node.js is also available if you need HyperFrames for animated overlays or kvidai API handoff during composition.

The best way is conversational editing: drop raw footage into a folder, tell your AI agent to "edit these into a launch video," and the agent inventories footage, proposes a strategy, executes cuts and grades, and renders a final mp4.

Yes, per-segment color grading and animated overlay composition are fully supported. The pipeline integrates HyperFrames or Manim to generate and overlay animations directly onto your video segments during the final assembly.

Yes, conversational video editing applies to talking heads, montages, tutorials, interviews, and travel footage. It handles transcription, loudness normalization, and cutting to produce polished content for creators, marketers, and editors.