DistilBook specs and limits

Last checked:

DistilBook turns a PDF, Word, Markdown or text file, pictures, a web page, a prompt or your own script into a narrated explainer video. A video uses up to 10 PDF pages or pictures on Basic, 30 on Pro, and unlimited on Max. A Guided Explainer (hand-drawn whiteboard) runs about 2 minutes per slide, up to 18 slides. A Motion Explainer (motion graphics) runs about 30 seconds per slide, up to 4 minutes on Basic, 6 on Pro and 10 on Max. Narration comes in 22 languages with 30 standard voices; Pro and Max add 20 premium voices and your own cloned voice. Output is an MP4 up to 1440p, 16:9 or 9:16, with subtitles and a share link. Generation costs 10 credits per slide, or per 3 slides in a 9:16 Motion Explainer.

What can you turn into a video?

DocumentsPDF, Word (.docx), Markdown (.md or .markdown) and plain text (.txt). PowerPoint, Keynote and older .doc files are not read: export them to PDF first.
File sizeUp to 500 MB per document. Pictures: up to 500 MB together.
PicturesJPG, PNG or WebP, in the Guided Explainer's Image tab. Each picture counts as one page toward your plan's limit.
Web pageA public link, in the Web URL tab of either format. Paywalled pages and pages that load their text with scripts can't be read; download them as PDF instead.
A promptIn the Motion Explainer's Prompt tab: describe the topic and DistilBook writes the script.
Your own scriptRead word for word. Motion Explainer: the Narration tab takes up to 10,000 characters, as one script or slide by slide. Guided Explainer: tick Use my text as the narration for a document or web page.

How many pages, slides and minutes can a video have?

PDF pages or pictures per video10 on Basic, 30 on Pro, unlimited on Max. A longer PDF is refused until you choose a page range under Select Pages (From and To); the video then uses only those pages.
Word, Markdown and text filesCounted at about 300 words a page against the same limit, so about 3,000 words on Basic and 9,000 on Pro. Page ranges work on PDFs only.
Guided Explainer (whiteboard)About 2 minutes of video per slide (80 to 150 seconds), up to 18 slides. The Length menu runs from 30 seconds to 20 minutes, and a custom length goes up to 35 minutes.
Motion Explainer (motion graphics)About 30 seconds per slide (22 to 45 seconds). Longest video: 4 minutes on Basic, 6 on Pro and 10 on Max (8, 12 and 20 slides in 16:9). The Length menu goes up to 6 minutes; a longer Max video comes from your own script in the Narration tab.
Words per slide3 to 469 words of narration per slide, in every language. A faster voice allows a little more.
Videos generating at onceUp to 3 per account. Videos waiting at the script review don't count.

Which languages and voices are there?

Narration languages22: English (US), English (UK), Spanish, French, German, Italian, Portuguese (Brazil), Dutch, Polish, Romanian, Indonesian, Turkish, Swedish, Russian, Finnish, Vietnamese, Ukrainian, Hungarian, Greek, Hindi, Arabic and Japanese.
Quality labelsAfter English, the language menu marks Spanish, French, German, Italian, Portuguese, Dutch, Polish and Romanian as Excellent quality and the other 12 as Good quality.
Source languagePick the narration language before generating. The source can be in a different language.
English accentsAmerican, British, Australian or Indian (optional).
Standard voices30 (14 female, 16 male), on every plan.
Premium voices20 more lifelike voices (ElevenLabs), on Pro and Max and with credit packs of $50 or more.
Your own voiceOn Pro and Max, and with credit packs of $50 or more. Record or upload 45 seconds to 5 minutes of your own voice (MP3, M4A, WAV, WebM or OGG, up to 20 MB). Pro keeps 2 cloned voices and can add 4 a month; Max keeps 5 and can add 10.
Narration delivery (Motion Explainer)5 styles: Explainer (the default), Professional, Documentary, Energetic and Storyteller.

Which styles, shapes and branding can you pick?

Guided Explainer styles5: Classic Whiteboard (the default, with optional slide templates), Mono Line Art, Sketch Notebook, Minimal Yellow Line and Hand-Drawn Education.
Motion Explainer styles20: Isometric Illustration, Mono Line Art, White on Navy, Earthy Organic, Soft 3D Coral, Sketch Notebook, Hand-Drawn Education, Bauhaus Poster, Cut Paper Collage, Doodle Color Pop, Editorial Flat Vector, Inkwash Journal, Ivory Navy Gold, Minimal Yellow Line, Navy & Red Editorial, Triangle Badges, DistiByte Terminal, Soft 3D Purple, Soft Blue SaaS and Duotone Indigo.
Visual instructionsUp to 2,000 characters of notes that steer the pictures on every slide.
Shape16:9 Landscape (the default) or 9:16 Portrait, in both formats. In a 9:16 Motion Explainer, each 30-second scene plays as 3 shorter slides.
BrandingYour logo and brand colours on every paid plan: Basic, Pro and Max.
Fixed once the video is madeStyle, voice, language and shape. To change one, make the video again.

What do you get at the end?

Video fileMP4 at 720p (HD), 1080p (Full HD, the default) or 1440p (2K). 1440p needs a paid plan.
WatermarkNone on Basic, Pro and Max.
SubtitlesDownload as .VTT or .SRT, or the transcript as .TXT.
Share linkVideos stay private until you share one. Sharing makes a public link anyone can watch in a browser, with no account.

What does a video cost in credits?

Generating a slide10 credits, charged when you approve the script. Writing, reading and editing the script before that is free.
9:16 Motion Explainer10 credits per 30-second scene, which plays as 3 slides.
AI picture edit5 credits per edit, for up to 5 marked areas of one slide picture. Placing your own picture into a slide is free.
AI rewrite of the scriptFree for now.
MP4 exportNo credits.
Plans and credit packsBasic, Pro and Max, plus one-time credit packs. Packs of $10 to $30 carry Pro page and length limits; packs of $50 or more carry Max limits, premium voices and voice cloning. Prices and credits per plan are on the pricing page.

What doesn't DistilBook do?

SCORM, xAPI or cmi5 packagesNot offered. You download an MP4 and add it to your LMS or authoring tool.
QuizzesNot offered. Videos play straight through, with no questions.
LMS completion trackingNot offered. DistilBook doesn't report who watched or finished a video to an LMS.
AI avatars or presentersNot offered. Scenes are illustrations and motion graphics with a voiceover; no person appears on screen.
PowerPoint and Keynote filesNot read directly. Export the deck to PDF and upload that.
Your own recorded voiceoverCan't replace the narration. The voice is always generated: a built-in voice or your cloned voice.
4K videoNot offered. 1440p is the highest export.

Common questions

What file types does DistilBook accept?

PDF, Word (.docx), Markdown and plain text files up to 500 MB, JPG, PNG and WebP pictures, a public web page, a prompt, or your own script. PowerPoint and Keynote files are not read directly; export them to PDF first.

How many pages can one video use?

10 PDF pages or pictures on Basic, 30 on Pro and unlimited on Max. For a longer PDF, choose a page range and the video uses only those pages. Word, Markdown and text files count about 300 words as one page.

How long can a DistilBook video be?

A Guided Explainer runs about 2 minutes per slide, with up to 18 slides and lengths up to 35 minutes. A Motion Explainer runs about 30 seconds per slide, up to 4 minutes on Basic, 6 on Pro and 10 on Max.

How many languages and voices does DistilBook have?

22 narration languages, with optional American, British, Australian or Indian English accents. There are 30 standard voices on every plan, plus 20 premium voices and your own cloned voice on Pro and Max.

Does DistilBook export SCORM or track completions?

No. DistilBook exports an MP4 video with VTT or SRT subtitles, which you upload to your LMS. There is no SCORM, xAPI or cmi5 package, no quiz and no completion tracking.

Does DistilBook use AI avatars?

No. Every scene is an illustration or a motion graphic with a voiceover, in a hand-drawn whiteboard look or a motion-graphics look. No presenter appears on screen.

What resolution and shape is the video?

An MP4 at 720p, 1080p (the default) or 1440p, with 1440p on paid plans, in 16:9 landscape or 9:16 portrait. There is no 4K export.

Where do you go next?