Source: raw/Claude_Design_Just_Unlocked_AI_Motion_Graphics.md — youtu.be/97Y5cz7H8SM, transcript fetched 2026-08-05. Creator: Futurepedia (16:14, published 2026-08-04; channel confirmed from the video page 2026-10-27). 2026-10-27 additions: raw/Simple_System_for_Better_Websites_with_Claude_Design.md and raw/Claude_Makes_a_New_Kind_of_Video_-_Full_Tutorial.md, two later videos from the same channel; see Later developments. 2026-10-28 addition: raw/Claude_Opus_5.5_Just_Changed_Design_Forever_5_Insane_Use_Cases.md (Ben AI, https://www.youtube.com/watch?v=6sZAZaQ5SNU, 14:11, published 2026-10-02); see Later developments.
Claude Design’s animations template is the least-discussed surface in the product and, per this creator, the one they use most — it is what produces the motion graphics in their recent videos. The distinguishing capability is not that it animates, but that it takes a timestamped transcript and returns animation synced to the spoken words, which turns the hardest part of explainer B-roll (matching visuals to narration timing) into an input rather than an editing task.
Key Takeaways
- Transcript-driven sync is the differentiator. Drop in a timestamped transcript and the output animation is cut to the words being spoken. Every other AI animation tool in this topic requires the sync to happen in the edit.
- It is a paid-plan feature. Requires Claude Pro or Max; reachable at
claude.ai/designor from the Claude sidebar. - Animations are one template among many — Claude Design also carries slides, mobile app design, UI mockups, resumes, and 3D objects. This article covers only the animations path.
- There is a progressive input ladder, and it maps directly onto how much brand control you need: bare prompt → single reference image → multiple reference images → a saved design system holding UI, logo, colors, and voice, selected per generation so every video matches.
- A vague prompt triggers a clarifying interview, not a bad output. The demo’s one-line brief (“animate a visual explanation of how LLMs are trained and how they work”) came back with a batch of questions — audience, duration, aspect ratio, label density — several of which can be answered “decide for me.”
- Post-generation controls are non-destructive. A tweaks panel swaps accent colors without regenerating, and a timeline at the bottom adjusts per-shot duration by dragging. This is the part that makes it usable in a real edit — you are not stuck re-rolling the whole animation to change one thing.
- Generation takes a few minutes for a 30-second 16:9 piece, per the demo.
The workflow the creator actually runs
- Select the saved design system for the channel (UI, logo, colors, voice) so output is on-brand by default.
- Paste the prompt describing the segment to illustrate.
- Drop in the timestamped transcript for that segment.
- Generate, then use the tweaks panel for accent color and the timeline for shot pacing.
- Cut the result into the edit as B-roll against the existing narration.
Try It
- On a Pro or Max plan, open
claude.ai/designand pick the animations template. - Start with a bare prompt to see the clarifying-question flow before investing in a design system.
- Build a design system once — UI, logo, colors, voice — and reuse it on every generation; this is what makes output consistent across videos rather than one-off.
- For explainer content you already have narration for, export a timestamped transcript and pass it in — that is the capability worth the plan.
- Use the tweaks panel and timeline before regenerating; most fixes do not need a new generation.
Later developments (2026-10)
- Same creator, later videos. On 2026-09-02 Futurepedia said the “exact prompts I use in Claude Design to make all the motion graphics that I actually use in my videos” are in a free Claude Design guide linked from his website video (
raw/Simple_System_for_Better_Websites_with_Claude_Design.md). The guide wasn’t fetched. - A no-Design route from the same channel. On 2026-10-19 he showed explainer videos made in an ordinary Claude chat: Claude writes plain JavaScript that draws each frame and the sound effects, driven by style prompts that carry an example video’s full source code (
raw/Claude_Makes_a_New_Kind_of_Video_-_Full_Tutorial.md). Details in Code-Drawn Explainer Videos in Claude Chat. He doesn’t compare it with the Claude Design template. - Transcript format, for that route: a word-level SRT for short pieces, or a line-level SRT for long ones because word-level files get “gigantic”. He gets it by dropping the audio into Claude and asking for a word-level SRT. This partly answers the format question below for the chat route. The Claude Design template’s own expected format is still unconfirmed.
- A second creator’s version, on Opus 5.5 inside the desktop app (Ben AI, 2026-10-02). His explainer prompt is short: a 15 to 20 second explainer, what it should cover, the aspect ratio, and “build it all in code”, with his design system selected. Two additions are worth copying. First, have Claude write a script and storyboard for approval before it builds. Second, ask it to add each scene separately inside the live artifact, so a comment can target one scene. With a single rendered video, he says, Claude “doesn’t know which part it is”. Then ask for an MP4 export in the chat.
- Retrofitting existing videos (same source). Ben built a skill that takes a YouTube link and a named section and replaces “the onscreen view with motion graphics, no captions”, animated to match what he says. He applied it to a static slide he had presented from. He says the skill can also transcribe, cut clips and add captions. The skill is in his free resources and wasn’t reviewed. This is the transcript-sync idea above applied after the video is recorded, rather than planned before.
- Logo intros. His prompt: animate the logo into a 2 to 5 second intro, “come up with five variations”, then export as MP4, for use as an intro or outro.
- Motion is now a separate first-party type. Claude Motion (Team and Enterprise, from 2026-10-08) is a code-animation artifact with MP4 export, separate from this Claude Design template.
Open Questions
- No export-format details — resolution, frame rate, file type, and whether there is an alpha channel for overlay use are not covered in the portion of the transcript captured. This determines whether it drops cleanly into an existing edit.
- No pricing or usage-limit detail beyond “requires Pro or Max” — how animation generations count against plan limits is unstated, which matters given the usage-limit pressure documented in Kahn v. Anthropic.
- Transcript format is unspecified. (Partly answered 2026-10-27 for the chat route: word-level or line-level SRT; see Later developments.) “Timestamped transcript” could mean SRT, VTT, or a plain timestamped text convention; the video promises to show how to get one easily but the format is not named in the captured section.
- No comparison against the topic’s code-based motion path. HyperFrames and Remotion render video from HTML/React with full determinism and version control; Claude Design animations trade that control for speed and a design-system UI. Which to reach for when is not addressed by either source.
- Maximum duration is untested — the demo is 30 seconds.
Related
- HyperFrames
- Remotion
- Code-Drawn Explainer Videos in Claude Chat (Futurepedia)
- Claude Motion Graphics — three methods
- generate Skill Instead of a Higgsfield Subscription
- Pre-Established Design with Claude (Ben AI) — the design-system and template set-up behind his explainers
- AI Video & Content Production
- AI Web Design
- Claude AI