10-minute narrated lesson from slides: Synthesia Basic vs Sume

A course creator usually wants the same thing: slides plus a voice, exported as a lesson video. On the page read today, Synthesia's Basic plan is $0 with 500 credits, which the page equates to about 10 minutes of video. Starter is $29 with 1,250 credits (about 12 minutes) and 3 personal avatars, and Pro is $89 with 6,000 credits (about 60 minutes). So a free 10-minute lesson is possible on Basic.

The same lesson on Sume

Sume has no presenter in this route. You export slides as images, narrate them with text to speech and render a Timeline. Assumptions are mine: about 900 characters of script per minute of speech, so 9,000 characters for 10 minutes.

Reading the result

Synthesia is cheaper for one lesson, because Basic is free. The Sume path starts to matter in three cases. First, you need more than one lesson a month: 500 credits is about 10 minutes, so each extra lesson means a paid plan, while on Sume the ninth lesson costs the same $1.43 as the first. Second, you do not want a presenter on screen. Third, you need to regenerate one slide's voiceover without redoing the whole lesson.

Constraints to respect

• Timeline stills are static holds, so animation within a slide has to be a video clip, not an image.
• Output width and height must be even numbers between 256 and 2160, and a render is capped at 1,800 seconds.
• A single text-to-speech request is capped at 20,000 characters, so a 10-minute lesson fits in one call, while a 30-minute one is split.
• If students need captions, a standalone captions job is $0.20 and covers videos up to 60 seconds, so for a long lesson use it on the short promotional cut.

The bottom line

For a single free lesson, use the free plan. For a repeating weekly lesson, count the minutes: at $1.43 for 10, a 40-lesson course is about $57, a fixed number you can plan a wallet top-up around.