Course Workshop & Avatars
Phase 3 · Speakers & Interaction
Who speaks the course, in which languages, with which voice — and where the speaker stands on every slide.
用途#
The figure comes before placing: when placing, it stands live on the slide, and you should see whom you are choosing the spot for.
使用方法#
操作路径CourseSpeakers & InteractionFigure & voice
- 1Open “Figure & voice”: choose a figure (default figure, your own figure from a photo or “My avatar”) (图 1).
图 1 “Figure & voice”: the chosen figure with its voice, optionally several speakers per slide range. - 2The voice belongs to the figure. Several speakers per slide range are possible (“Slides 1–3 spoken by A, 4–8 by B”).
- 3Below it is the course's voice model: “Voice model: new (v4)” or “Voice model: previous”. New courses speak with the new model; an existing course only switches via “Switch to the new voice model” and a confirmation.
- 4Define languages: per language “full” (whole course as video, at most two), “start” (the first slides are ready, the rest is created while watching) or “off”. The estimated rendering costs are shown below, with their derivation (图 2).
图 2 The course's languages: per language “full”, “start” or “off”, below them the estimated rendering costs. - 5“Placing”: decide per slide where and how large the speaker stands (see speaker spot).
设置与开关#
功能目录中没有独立开关——该功能属于其所在环境。
Head start instead of waiting#
Production runs ahead of the viewer: for languages in “start” mode the first slides are ready as video. If someone switches to this language, video plays immediately, and the rest is created while they watch. This way a course saves a large part of the rendering costs without anyone waiting.
When re-rendering happens#
Changed narration orders the avatar video of that slide again. A different voice version or cast, on the other hand, does not change finished videos by itself; they are only re-rendered after explicit approval.
The course's voice model#
Every course remembers which voice model it is voiced with. Courses created before 17.10.2026 and courses from files stay with the previous model — also for new slides, new variants and new languages. This way the voice never changes in the middle of a course. Newly created courses speak with the new model (v4) from the start.
Live answers in the course (Ask me, tutor, presentation view) follow the course's voice model; a course with the new model answers with its real-time variant.
Switching is only possible explicitly under “Figure & voice” → “Voice model” and can be undone. Recordings already stored remain in use until new voicing is approved; until then a switched course can contain slides of both models.
提示#
- A new cast applies to videos created from now on. Finished videos are never re-rendered on their own — only after approval.
- In the trial account the default figure speaks with its own voice; your own figures are available in your own organisation.
- Switching the voice model orders nothing: slides already voiced and finished videos remain unchanged; new voicing only happens after approval.
亲自试用#
相关功能#
- Avatars & voicesYour own figures from a photo and your own voices from a recording — with consent as a condition and one fixed rule: every face speaks only with its own voice.
- My avatarLecturers make themselves the speaker of their courses: consent, photo or video selfie, voice, test, use — revocable at any time.
- Speaker spotDecide slide by slide where and how large the speaker stands — and whether at all. The calculation makes a suggestion, the author approves.
- Further languagesThe interface in fifteen languages and a language switcher for every user — plus subtitles and presentation in the chosen language.