NotebookLM Video Overview or a lesson video: which fits a teacher

NotebookLM turns sources into Cinematic, Explainer or Short videos. When a teacher needs their own script and slides, build the lesson with Sume.

4 min readSume
All posts

Use NotebookLM's Video Overview when you want a fast, auto-made explainer of sources you already have, and use Sume when you need a lesson you control line by line: your own script, your own slides, a captioned file you can reuse. They answer different needs. Google's tool decides the storyline from your sources; Sume assembles what you provide.

What does NotebookLM's Video Overview do?

According to Google's help page, you can turn sources uploaded to a notebook into a video. There are three formats: Cinematic (rich and immersive, 18+ only, English narration), Explainer (a structured, comprehensive overview) and Short (about 60 seconds, for quickly grasping key concepts). Explainer and Short support more than 50 languages; Cinematic is English only.

You can steer the result by format, language, visual style and a steering prompt. Styles include Classic, Whiteboard, Watercolor, Retro Print, Heritage, Paper-craft, Kawaii and Anime, or you can describe one. The videos can be downloaded as files, though Google notes that some sources, such as Play Books ebooks, may restrict downloading.

Where does a teacher need something else?

The tool writes the script for you. That is the strength, and also the limit for a lesson that must match a curriculum, a textbook page or a district's wording. The table sets the two side by side. Sume values are from the Sume docs; NotebookLM values are from Google's help page, read 2026-10-03.

NotebookLM Video Overview (Google help, read 2026-10-03) against a Sume lesson build (Sume docs).
QuestionNotebookLM Video OverviewSume lesson build
Who writes the narration?The tool, from your sourcesYou, as the avatar script or your own audio file
LengthShort is about 60 secondsAvatar clip 4 to 60 s; Timeline up to 1800 s
Visual lookPreset styles or a custom descriptionYour slides and clips as Timeline slots
Languages50+ for Explainer and ShortSet language for captions; check your voice's support
ReuseDownload the videoSame slots can be re-rendered with new audio

How would I build a lesson with Sume?

Write the script in short scenes. Each avatar talking video takes an estimated duration of 4 to 60 seconds, so a 6-minute lesson is a set of scenes that you join. Put the slide images as stills in Timeline 1.0 slots, set the narration as the audio spine, and use audio.parts[] (up to 20 gapless slices) when the narration comes in pieces. Timeline costs $0.10 per output minute.

curl -X POST https://api.sume.com/v1/timeline-1.0/render \
  -H "Authorization: Bearer $SUME_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: lesson-001" \
  -d '{
    "audio": { "url": "https://media.sume.com/artifacts/artf_vo/lesson.wav", "duration_seconds": 120 },
    "output": { "width": 1920, "height": 1080 },
    "video": [
      { "source_url": "https://media.sume.com/artifacts/artf_s/slide1.png", "start": 0, "duration": 60, "fit": "contain" },
      { "source_url": "https://media.sume.com/artifacts/artf_s/slide2.png", "start": 60, "duration": 60, "fit": "contain",
        "transition": { "type": "fade", "duration": 0.25 } }
    ]
  }'

When is each one the better call?

Pick NotebookLM for a quick study aid from a pile of notes, for multilingual summaries, or when a student wants a short overview. Pick Sume when the teacher's exact words matter, when the file must be 16:9 for a classroom screen, or when you need captions on a file that is not tied to a notebook. A teacher can also do both: generate an overview to see how a topic might be explained, then write their own script with the same structure and build it. Either way, read the output before students see it; both tools can get a fact wrong, and the teacher stays responsible for what is taught.

Sources

Related posts

More in Use cases

All Use cases posts

Written by Sume