Skip to content

manimvox

Explainer videos made by your AI agent.

Ask Claude Code, Codex, Cursor or Gemini CLI for "an explainer video of" a paper, a codebase, an idea or a pull request. manimvox gives the agent what it needs to research the topic, write a cited script, animate it with Manim, narrate it with a text-to-speech voice, and check the result before it ships. You direct; the agent does the work.

The manimvox logo draws itself, then four things manimvox animates: a ball rolling down a 3D loss surface, a request flow, a bar ranking and a code diff

Made with manimvox: four of its blocks. Finished videos made by AI agents are in the gallery.

Get started

uv tool install "manimvox[kokoro]"   # 1. install, with the offline voice
                                     #    (or: pip install "manimvox[kokoro]")
manimvox skills install              # 2. give your agent the skills

Then ask your agent: "make an explainer video of <paper / repo / idea / PR>".

  • How it works: what the agent does, the checks it must pass, and why manimvox is built this way.
  • Install: requirements for Linux, macOS and Windows, and the optional extras.
  • Make a video with an agent: the skills, the workflows, and the tools for Python agent frameworks.
  • Write an episode by hand: the same library, without an agent.
  • Gallery: finished videos, with the prompts and projects that made them. Start with Made by your agent, a short introduction to manimvox made with manimvox.
  • Python API: every component, clip adapter and tool.

Features

  • Made for AI agents. Eleven agent skills cover four workflows (a document, a concept, a codebase playlist, a pull request), and every command is also a typed tool for Python agent frameworks. It never prompts without a terminal, its errors are one line, and downloads need --yes.
  • One episode file in, one finished MP4 out. It comes with subtitles (.srt), and narration and picture stay in step.
  • Ten voice engines behind one interface. Kokoro is the default, and it runs offline with no key. Piper, macOS say, edge-tts, OpenAI, ElevenLabs, Sarvam AI and Gnani.ai (for Indian languages), and the XTTS-v2 and F5-TTS voice cloners are also supported.
  • Checks that gate a render:
  • text contrast against the background (WCAG 2.1);
  • text off the safe stage or overlapping;
  • silent narration lines;
  • contact sheets for a quick look.

Every failed check exits non-zero. - 3D when depth is the idea: Episode3D adds Manim's tilting, orbiting camera to an episode, with the header and progress bar kept flat on screen. - Screenshots and screen recordings: for product demos and UI changes. The agent captures with its own browser or computer-use tools; manimvox zooms into a region, spotlights it, adds callouts and an animated cursor, all timed to the narration. - 3D models from files: a glTF (Blender's export), OBJ or STL model drawn by Manim so its camera orbits it and parts can be picked out (the mesh-model block), or rendered with real lighting and animations as a clip (from_model). - A theme per video: colours and fonts come from the project's series.json, never from a fixed preset. - Cross-platform: macOS, Linux and Windows, with no system ffmpeg (audio and video are decoded with PyAV).