Create a short pause around one question. A solid speech balloon settles into place, reveals the complete phrase and holds beside a dimensional thinking-face image. One small turn of the face suggests consideration before the scene becomes still. This 5.2-second graphic is designed to cut into an explanation and leave its last reading frame usable.
What you get
A local generator, editable HyperFrames question shot and motion/review instructions. Generate the composition from your question and the supplied illustration, then render a 5.2-second segment for your edit.
One question input and a thinker raster slot with a bundled generated default. The balloon body and tail form one editable SVG path; the dimensional character remains an actual image. No presenter footage or alpha matte is required.
Clear canvas through 0.16 seconds, balloon entrance through 0.44 seconds, complete-phrase reveal from 0.25 to 0.43 seconds and thinking-face entrance from 0.33 to 0.69 seconds. A small angle change from 1.05 to 1.55 seconds leads into a still hold through 5.20 seconds.
Four styles keep the same data and choreography: White & Yellow (white-yellow), Charcoal & Lime (charcoal-lime), Paper & Orange (paper-orange), and Black & White (midnight-ice). Semantic style overrides are supported; check contrast after changing them. Dark canvases use a fine grid. Local fonts include Inter, IBM Plex Mono for measurements and ordinals, Smiley Sans and Noto Sans SC. Chinese text selects Smiley Sans automatically, including accompanying Latin text; --zh-font noto-sans-sc selects Noto Sans SC, while --font takes precedence for a supplied font.
Before you choose
Ask a question that earns a pause and can be read at the intended viewing size. Judge the complete sentence, not just whether it fits; the balloon and thinking image should create room for reflection rather than compete with dense copy.
Good fit
A creator pausing an explanation to ask one focused question before moving to the answer.
A short teaching passage that needs a readable reflection beat rather than simulated typing.
A series of prompts or chapter questions needing consistent illustration, balloon geometry and type.
Not for
Answering the question, collecting responses or creating an interactive chat interface.
Long passages beyond the 110-character input limit, indefinite automatic shrinking or repeated floating/typing effects.
Automatic long-form editing, generating a missing presenter or soundtrack, or copying another creator’s identity and source assets.
How to use
You say/creatormotion-type-question-bubble Turn my supplied explanation into a white-yellow B-roll scene using the Question Bubble Pause effect. Use the text, data and media I provide, and ask for any required input that is missing.
Write an original question of 1–110 characters after trimming. The current implementation enforces that limit. Keep it short enough to understand during the pause; split a longer passage into another shot instead of trying to fit an entire paragraph.
Reuse the bundled thinker image or replace the exact slot through --images MAP.json with a local raster. Relative paths resolve beside the map and unnamed defaults remain. Follow the image policy; do not substitute a text emoji or embedded SVG for the dimensional image.
No presenter file is needed. The question reveals as a complete phrase, with length-based font sizing and additional fit adjustment. Inspect the actual line wrapping: text belongs inside the balloon body and must not run over its tail. Black & White desaturates the face inside the composition.
From the extracted package, prepare Node.js 22+, FFmpeg and HyperFrames CLI 0.8.30. Run node scripts/create.mjs --out PROJECT --data CONTENT.json --style white-yellow, substituting another documented palette if wanted. Read the motion specification and image policy before adapting the scene; use semantic --overrides for deliberate style changes. Add --images MAP.json only when replacing thinker. Retain all media, fonts and scripts locally.
Inspect the editable project at entry, each motion handoff and final hold, then render with the command printed by the generator. Check the resulting frames for text collisions, correct numbers and readable contrast. Keep at least 1.2 seconds for the final reading when editing, and compare all four palettes with identical content after structural changes. Narration, music and assembly into a longer film remain separate work. Inspect both tail roots, the tip’s clearance from the face, the complete question and the final frame at small viewing size. Preserve a quiet still hold and a usable ending; do not add an empty fade, looping bounce or character-by-character typing.
Requirements and costs
You bring
question: provide your own content or retain the illustrative default.
Dependencies
HyperFrames CLI 0.8.30 or compatible — required · Node.js 22 or newer — required · FFmpeg — required
Outside costs
Not collected yet
Tools used
HyperFrames
Publisher testing
v1.0.1 — Claude Code / Claude Desktop / Cowork / Codex / ChatGPT
FAQ
Yes. question is the text input and the package supports four palettes and semantic overrides. Longer questions use smaller type, but actual wrapping still needs review within the fixed body.
No. This is a graphic-only scene. It needs the thinker raster, for which a generated default and provider provenance are bundled; a local image map can replace it.
Yes. Keep the fast balloon entrance, whole-phrase reveal, one small consideration beat and still final hold. Render and inspect the edited timing and balloon/image clearance.
Empty text or more than 110 characters is rejected. Within the limit, font size steps down and a fit routine can shrink it further; this is not a guarantee that dense copy will read comfortably.
The pause is its purpose. The last question frame stays available for an editorial cut, allowing the next shot to supply the answer or continuation.
User reviews
—0 reviews
Select a star to share your experience.
No reviews yet. Ratings appear once readers share real experiences.