What problem does it solve?
Creating Manim animations with synchronized voiceover is traditionally time-consuming, requiring manual audio editing to align narration with animation beats and extra steps to fix audio playback issues across common media players like VSCode and Chromium. This Skill automates the entire end-to-end workflow, eliminating manual alignment and playback troubleshooting.
Core Features & Use Cases
- Automated Voice Synthesis: Uses free edge-tts (no API key required) to generate voiceover in multiple languages including English and Turkish, with caching to avoid regenerating identical audio.
- Auto-Paced Animations: Includes a reusable NarratedScene base class that automatically adjusts animation timing to match the duration of each narration segment.
- Live Asset Integration: Optionally pre-fetches screenshots of real websites, GitHub PRs, or dashboards via gstack to include live visual content in walkthrough videos.
- Reliable Playback: Handles proper audio re-encoding with ffmpeg to ensure final MP4 files play correctly with synchronized audio in all modern players.
- Use Case: Create a 60-second PR walkthrough video that narrates code changes while showing live screenshots of the GitHub pull request, with no manual audio editing or screenshot capture required.
Quick Start
Use the manim-narration skill to create a 30-second narrated Manim video explaining how binary search works, with a Turkish female voiceover and cinematic transitions.