- Home
- Reverse Engineering Tools
- Chalkboard
Chalkboard
What it is
Chalkboard turns a prompt into a narrated whiteboard-style explainer video and exports an MP4. It supports 16:9 explainers, vertical short-form reels, and cinematic documentaries that research topics and add cited sources to scripts. Productions can be dubbed into multiple languages in one run, with subtitles set to a different language from narration. Script generation works with Anthropic, OpenAI, or local Ollama; narration supports Piper, OpenAI, and ElevenLabs. Chalkboard creates hand-drawn diagrams, supports SVG artwork, and can generate images with OpenAI’s gpt-image-2. Subtitles and mood-matched background music are enabled by default, with Jamendo selection or user-supplied tracks available. The project offers a command-line interface, library, HTTP API, and web studio, and runs self-hosted on the user’s machine. Ollama and Piper can provide local generation at zero marginal cost per video. Generated images require an OpenAI API key and incur costs; image generation can be disabled or capped. Chalkboard is MIT-licensed, and server-side API keys remain hidden from the web UI.
For and against
For
- Exports narrated MP4 videos
- Supports multiple video formats
- Multilingual dubbing and subtitles
- CLI, library, API, and web studio
- Local providers available
Against
- Generated images incur OpenAI costs
- Image generation requires an API key
- Self-hosted setup required
The verdict
Chalkboard combines prompt-based scripting, narration, diagrams, subtitles, music, and several delivery interfaces. Local providers can avoid per-video provider charges for some tasks, but generated imagery has separate OpenAI costs.
Who it suits
It suits creators and teams producing narrated explainers, reels, or researched documentaries. Self-hosting and local providers suit users who want local generation options.
Plans and prices
Free
MIT-licensed software · local providers available at zero marginal cost per video
Read 9 Oct 2026 · github.com
On the record
- AI providers
- Script generation supports Anthropic, OpenAI, and local Ollama; narration supports Piper, OpenAI, and ElevenLabs.github.com · read 9 Oct 2026
- Audio
- Subtitles and mood-matched background music are enabled by default, and users can choose Jamendo music or provide their own track.github.com · read 9 Oct 2026
- Cost limits
- Generated images require an OpenAI API key and incur costs; the README says image generation can be disabled or capped per video.github.com · read 9 Oct 2026
- Languages
- A production can be dubbed into multiple languages in one run, with subtitles in a language different from the narration.github.com · read 9 Oct 2026
- License
- Chalkboard is released under the MIT License.github.com · read 9 Oct 2026
- Purpose
- Chalkboard turns a prompt into a narrated, whiteboard-style explainer video exported as an MP4.github.com · read 9 Oct 2026
- Research
- The Cinematic mode researches topics and injects cited sources into the script to ground the narration.github.com · read 9 Oct 2026
- Security detail
- The README says API keys are read from the server environment and the web UI never sees them.github.com · read 9 Oct 2026
- Self-hosting
- The project runs on the user's machine and can use Ollama and Piper for local script generation and narration at zero marginal cost per video.github.com · read 9 Oct 2026
- Video formats
- It supports 16:9 explainers, vertical short-form reels, and research-backed cinematic documentaries.github.com · read 9 Oct 2026
- Visuals
- It creates hand-drawn diagrams and can generate images with OpenAI's gpt-image-2; SVG art is also supported.github.com · read 9 Oct 2026
- Ways to use
- The project provides a command-line interface, a library, an HTTP API, and a web studio.github.com · read 9 Oct 2026
