linyqh/NarratoAI

利用 AI 大模型,一键解说并剪辑视频

What it solves

NarratoAI is a one-stop automated tool for creating movie and TV show commentary videos. It eliminates the manual effort of writing scripts, editing video clips, generating voiceovers, and adding subtitles, streamlining the entire content creation process for creators.

How it works

The tool leverages Large Language Models (LLMs) to handle the creative and technical aspects of the video production pipeline. It uses vision-capable LLMs (like Qwen2-VL or TwelveLabs Pegasus) to understand video content, generates a script based on that understanding, and then automates the editing, voiceover generation (via various TTS engines), and subtitle synchronization.

Who it’s for

Content creators and social media influencers who want to produce high-quality movie/TV commentary videos efficiently without needing professional editing skills.

Highlights

  • End-to-end Automation: Automates scriptwriting, editing, voiceover, and subtitles in one workflow.
  • Video Understanding: Supports advanced models like Qwen2-VL and TwelveLabs Pegasus for deep video analysis.
  • Voice Cloning: Integrates multiple TTS engines, including IndexTTS and OmniVoice, supporting voice cloning and emotional control.
  • Flexible Deployment: Available as a cloud version, Docker containers, or local installation packages for Windows and macOS.
  • Integration: Supports exporting drafts to CapCut (剪映).

Related

  • Project
  • Project
  • Project
  • Project
  • Project