ManimCommunity/manim-voiceover

Manim plugin for all things voiceover

What it solves

Manim Voiceover simplifies the process of adding audio narration to Manim animations. It eliminates the need for external video editing software by allowing users to integrate voiceovers directly within Python code, synchronizing animations with spoken words in real-time.

How it works

The plugin integrates with various Text-to-Speech (TTS) services (such as Gemini, Azure, gTTS, and pyttsx3) to generate AI voices or allows users to record their own voice via a command-line interface. To achieve precise timing, it uses OpenAI Whisper to provide per-word timing for animations, ensuring that visual elements trigger exactly when specific words are spoken.

Who it’s for

Educators, content creators, and developers using Manim to create mathematical or technical animations who want a streamlined workflow for adding synchronized audio narration.

Highlights

  • Integrated Workflow: Add voiceovers directly in Python without using a video editor.
  • AI Voice Support: Integration with multiple TTS services including Gemini and Azure.
  • Precise Timing: Per-word animation triggers powered by OpenAI Whisper.
  • Live Recording: Ability to record voiceovers via the CLI during rendering.
  • Multilingual Support: Integration with machine translation services like DeepL for translating voiceovers.

Related

  • Project
    corvo007/MioSub

    An AI-powered subtitle editor that automates transcription, translation, and millisecond-precise timeline alignment using Gemini and Whisper.

  • Project
    kadirnar/whisper-plus

    A comprehensive audio and video processing toolkit that extends OpenAI's Whisper for transcription, speaker diarization, summarization, and RAG-based video chatting.

  • Project
    zh-plus/openlrc

    A Python library that transcribes audio using faster-whisper and uses LLMs to translate and polish the text into synchronized .lrc subtitles.

  • Project
    collabora/WhisperLive

    A real-time transcription application that uses OpenAI's Whisper model to convert live speech input from microphones or streams into text with minimal latency.

  • Project
    jasoncheng7115/jt-live-whisper

    A fully local AI toolkit for real-time speech transcription, translation, and meeting summarization that works across any system audio source without cloud APIs.