GPT-Live-1.1 voice update
Arrange different voices as a roll call: the camera finds groups of phones, captions provide replies, and a final phone appears alone.
View HTML source
<!doctype html><html lang="zh-CN"><meta charset="utf-8"><meta name="viewport" content="width=device-width,initial-scale=1"><title>GPT-Live-1.1 voice update · sequence</title><style>html,body{margin:0;width:100%;height:100%;overflow:hidden;background:#f3d4c3}canvas{display:block;width:100%;height:100%;object-fit:contain}</style><body data-mode="sequence"><canvas width="1000" height="600"></canvas><script src="data.js"></script><script src="common.js"></script><script src="scene.js"></script><script src="bridge.js"></script></body></html>Motion and composition
Local motion · Composition rules
Stage the phones like performers

Arrange phones in pairs on a warm-colored surface, with stage-colored blocks framing the top and bottom. Give each voice orb its own color and fix small sans-serif captions below.
Introduce one group per pan
View HTML source
<!doctype html><html lang="zh-CN"><meta charset="utf-8"><meta name="viewport" content="width=device-width,initial-scale=1"><title>GPT-Live-1.1 voice update · sequence</title><style>html,body{margin:0;width:100%;height:100%;overflow:hidden;background:#f3d4c3}canvas{display:block;width:100%;height:100%;object-fit:contain}</style><body data-mode="clip" data-start="4" data-end="23"><canvas width="1000" height="600"></canvas><script src="data.js"></script><script src="common.js"></script><script src="scene.js"></script><script src="bridge.js"></script></body></html>Let the camera settle before the current phone responds. Pan in the same direction before the next response, switching phones and captions together; keep other groups quiet.
The final phone breaks the repeated rhythm
Paired arrangements establish an expectation; switch to one phone near the end and give it a separate pause before closing on the feature name.
Characters and dialogue are replaceable
Adapt to introductions of assistants, services, or people. Plan each exchange and the final special character first, then add captions and voices; keep each group's color and identity consistent.
Sections and rhythm
Click a section to seek to it in the choreography example above.






Visual references · Discrete still frames
Creating other themes
- Suitable for introducing multiple characters or features; preserve turn-taking and the final special character.
- Caption timing must be aligned with voices separately.
Production constraints
Stage surface / Phone pairs / Colored voice orbs / Captions / Panning camera
- Repeated lateral movement finds different phone groups, introducing voices like a cast roll call.
- Each phone's orb color identifies a different voice group, while captions show turn-taking.
- Switch from pairs to one phone for a rhythmic contrast near the end, then cut to a white closing frame.