Synthesia 3.0 clickable branching video: what Sume can do instead

Synthesia 3.0 lists clickable calls to action and branching. Sume renders linear avatar clips, so branches are separate clips that your own player links.

5 min readSume
All posts

Synthesia's 3.0 announcement lists clickable video elements, including calls to action and branching options. Sume does not make clickable or branching video: each Avatar 1.0 job returns one linear MP4, so a branching experience is a set of clips that your own page or player connects.

What Synthesia states

From the Synthesia 3.0 announcement, read 2026-10-02:

  • The post also names Copilot and Courses as coming in 2026; this article does not rely on them.
Synthesia 3.0 items relevant to interactivity (read 2026-10-02)
ItemStated detail
InteractivityClickable video elements including calls to action and branching options
Video agentsInteractive AI that holds real-time conversations within videos
Scale claims240+ avatars in 160+ languages

What a Sume avatar clip is

A Sume avatar video is a rendered file, 4 to 60 seconds, from a ready avatar and a script or multi-scene video_inputs. It has no hotspots, no branching graph and no live session. Optional inline captions are burned into the MP4.

That makes it a good building block for a branch, because each branch is short and reusable.

Building branches yourself

Write each branch as its own script, render with the same avatar_handle so the presenter matches, and host the MP4s. Your page supplies the buttons and decides which clip plays next. Use idempotency keys per branch so a retry never pays twice, and track each job as in Jobs and results.

  • One intro clip, then one clip per choice.
  • End each clip on a held frame so the cut to the next feels intentional.
  • Keep branches under 60 seconds, or split them.
  • Store the job id next to each button in your own data.

Choosing

If clickable elements inside the video player are the requirement, Synthesia lists them and Sume does not. If you already own the page and only need many consistent presenter clips, Sume's per-job rendering fits, and the interactivity lives in your front end.

Sources

Related posts

More in Comparisons

All Comparisons posts

Written by Sume