HyperFrames and Draft: what's the difference?
Both draw scenes in HTML and GSAP. HyperFrames is open source you run yourself; Draft is a service whose servers handle voice, footage, rendering and publishing.
Pick HyperFrames when
Running the render pipeline yourself as open source
Pick Draft when
Making videos with agents and publishing them right away
What you handle separately with HyperFrames
- Local Chrome and FFmpeg
- TTS generation
- Stock and image search
- Background music
- Caption alignment
- Upload and scheduling
In Draft, one place
Web editor plus one MCP connection- Plan and script
- AI voice
- Footage
- Motion graphics
- Captions
- Rendering
- Upload and scheduling
- Automation
Why teams pick Draft
No environment to set up
No CLI, Chrome or FFmpeg to install. Draft's servers render and return a preview link.
Fewer tokens on plumbing
Your agent doesn't handle TTS, stock search, music, caption alignment and upload through separate APIs. One tool call is one server job.
People can edit too
Agent-made videos stay as projects in the editor, so teammates who don't code can change text, timing and footage on screen.
HyperFrames vs Draft
As of November 2026
| Feature | HyperFrames | Draft |
|---|---|---|
| Scene authoring | HTML, CSS, GSAP | HTML, CSS, GSAP plus blocks and styles |
| Open source and self-hosting | Apache 2.0, run it anywhere | Hosted service |
| Price | Free (you pay for infrastructure) | Start free, pay credits for what you use |
| Render environment | Set up local, Docker or your Lambda | Draft's servers |
| AI voice, stock, music | Bring your own | Built in |
| Editor for people | Edit code | Timeline and scene editor |
| Social publishing, scheduling, automation | Build it yourself | Built in |
What changes with Draft
Instead of finding and wiring tools together, finish in one service that keeps getting better.
No more tool hunting
Script, AI voice, stock and generated footage, editing, rendering, publishing and automation in one account with one credit balance. No sign-ups and API keys per service.
Nothing to install, always improving
No skills or open-source projects to download and configure. As new models and techniques arrive, Draft keeps raising quality and value.
Blocks save tokens and cost
Our own block registry (34 blocks, 3 styles) means scenes aren't coded from scratch. Send a block name and copy, the server draws it, and block scenes and restyling are free.
Same benefits however you work
MCP from Claude, ChatGPT or Codex, the REST API, automations or the web editor all use the same blocks, rendering and publishing.
Coding each scene yourself
Dozens to hundreds of lines of HTML, CSS and GSAP per scene
With a Draft block
Just a block name and copy. The server handles drawing, animation, captions and transitions
{
"type": "number",
"from": "208 billion switches",
"data": {
"numbers": [
{ "value": "208", "unit": "B", "label": "One B200 chip" }
]
}
}Which one should you pick?
Pick HyperFrames when
- You want to run the whole render pipeline as open source on your servers
- You're embedding a video render engine in your own product
- You already have TTS, footage and uploads covered by other systems
- You want cost to be infrastructure only
Pick Draft when
- You want agents to make video without setting up a local environment
- You don't want to integrate voice, footage, captions and music yourself
- Teammates who don't code need to edit the results
- You want to publish to social platforms right away and repeat daily
FAQ
Can I do my HyperFrames work with Draft in Claude Code?
Yes. Connect the Draft MCP server to Claude Code or Codex: the agent writes scenes in HTML, and Draft's tools handle TTS, stock, rendering and upload. The connect page shows how.
Can I bring HyperFrames HTML into Draft as is?
Both use HTML and GSAP, so scene code moves over fairly easily, but there's no automatic converter. Project structure and asset paths need to follow Draft's format.
Which is cheaper?
HyperFrames is free; you pay only for render infrastructure. Draft charges credits for work you run, like TTS, AI generation, rendering and publishing. If you have people and time to operate it yourself, HyperFrames costs less; if you'd rather save that time, Draft comes out ahead.
Does the render match the browser preview?
Draft renders from the same scene source as the editor preview, and you can check frame snapshots before rendering. HyperFrames is also designed so the same HTML produces the same result.
Does an agent really use fewer tokens?
It depends on the job. Writing scene code costs about the same, but the agent no longer handles voice, stock search, music, caption alignment and upload through separate APIs, so the conversation gets shorter by that much.
Can teammates who don't code use it?
HyperFrames is edited through code or an agent. In Draft, the same video opens in the editor and can be changed with clicks and chat.
Weighing something else too?
What people with the same question read next.
Making videos in code: is Remotion or Draft the better fit?
Code every frame in React, or start from an AI-made video and adjust it. Strengths and limits of both.
ReadHeyGen vs DraftDo you need a talking avatar, or would graphics explain it better?
A person talking, or the content on screen? The answer changes the tool. Both approaches compared.
ReadOpusClip vs DraftPosting Shorts daily: cut a long video or make new ones?
Got long footage to cut? OpusClip. No footage? Draft. The difference, and how to use them together.
ReadMake your first video now
Start free with no subscription and top up credits only when you need them.
Start free