Book to Video

Paste chapter one of your book, choose TV Series for a season or Film for a single adaptation, and read the summary before you go on.
| SceneMixer at a glance | What you get |
|---|---|
| Video price | From $0.06 a second (10 credits) on the default tier, up to $0.47 a second on the top tier; every price is shown before you press the button |
| Clip length | Up to 30 seconds per generated segment; an episode is composited from its segments at 1 credit a second |
| One episode, worked out | A 60-second episode on the default tier is about 660 credits (video plus compositing), about $4.11 at the lowest credit price; a 10-episode series of 90-second episodes from a 30,000-character novel is about 10,026 credits, about $62 |
| Dialogue | Spoken in the video itself, one voice per character, in any of 15 languages |
| Formats | 9:16 vertical or 16:9 landscape; 480P to 1080P, plus a 2K tier |
| Free to start | 50 credits on signup, 15 free setup images, a free storyboard for the first episode and a free 5-second video preview |
| Who uses it | 2,900+ creators have generated with SceneMixer (accounts with at least one generation, counted November 2026) |
| Input | The text of a book you wrote or have the rights to; .txt, .docx and .md uploads; a long book is split into volumes with the same cast |
Which books work
| Kind of book | Works as | Notes |
|---|---|---|
| Your own novel | A series, one chapter or two per episode | The usual case; novel to video covers web novels in depth |
| A memoir or family history | A short film or a few episodes | Invented faces for real people unless you have their consent |
| A children's picture book | A short cartoon | A drawn look such as Watercolor Storybook |
| A public-domain classic | An adaptation in any style | Check the text is public domain where you publish |
| Non-fiction | Dramatized scenes | Works when there are people and moments; pure argument does not |
The book must be yours or licensed to you. Famous characters from other people's books, and well-known film versions of them, are refused by the IP check. IP check.
How a long book is read
Up to 10,000 Chinese-equivalent characters a script is read in one pass; beyond that, in two passes: first the cast, places and props, then the structure, with each episode's outline expanded when you open it. That is how one project can take 300,000 characters of English. Past that ceiling the box refuses the text rather than cutting it off silently; split the book into volumes. Long scripts read in two passes and length caps.
Files: paste the text, or drop .txt, .docx or .md. PDFs and e-book files are refused; export or copy the text. Which files work.
One cast across volumes
Each volume is its own project, but the cast does not have to be redrawn. Pick existing characters, scenes and voices from your library in the next project, and the hero of volume two has the face from volume one. Reuse characters across projects.
Adaptation choices you make
- Type: TV Series for a season of 300-second episodes; Short Drama for a vertical, hook-driven cut; Film for one long adaptation.
- Narration: keep the narrator's voice as voice-over lines, or let scenes play with dialogue only.
- Region and language: the same book can be cast for another market and spoken in another of the 15 dialogue languages. Second language version.
- Trailer first: a 60–120 second book trailer is a cheap way to test the look. Book trailer.
What a book costs to adapt
The reading is small; the video is not. A season of ten two-minute episodes is 1,200 seconds of video at 10 credits a second on the default tier, plus 1 credit a second for joining. Make episode 1, watch it, fix the cast, then decide on the rest. What a micro-drama costs.
Languages
Native dialogue in 15 languages
Every series below was produced by the same pipeline with the cast speaking that language natively: the interface, the working documents and the spoken lines are all in one language, and nothing is dubbed. Open one to hear it.
A Carta de LisboaPortuguêsNative dialogue
윈터 프라미스한국어Native dialogue
El Secreto de CostaEspañolNative dialogue
浪人の誓い日本語Native dialogue
Ikrar JakartaBahasa IndonesiaNative dialogue
Зимняя коронаРусскийNative dialogue
L’Héritier du DéfiléFrançaisNative dialogue
Il Tavolo dell'OlivaItalianoNative dialogue
De Vuurtoren van de FjordNederlandsNative dialogue
العهد الصحراويالعربيةNative dialogue
Çantasındaki SözleşmeTürkçeNative dialogue
Die Istanbul-TäuschungDeutschNative dialogue
Останній сигналУкраїнськаNative dialogue
問劍青雲繁體中文Native dialogue
The Last EnvelopeEnglishIn your language
In SceneMixer vs. stitching tools together
Most AI drama workflows are five or six tools in a row. This is where each step happens here, and what it replaces.
| Step | In SceneMixer | Doing it by hand with separate tools |
|---|---|---|
| Script and episode plan | Paste a script or a novel, or type one line: it is read into a cast, locations, props and an episode outline you can edit | A chat model writes the script; you split it into episodes and carry the text from tool to tool |
| Character faces and places | Every character, location and prop is drawn once as a reference sheet and attached to every shot it appears in | An image model, one sheet at a time; you upload the right reference to every clip yourself |
| Shots | A storyboard per episode with numbered shots and seconds; video is generated segment by segment in 9:16 or 16:9 against the same sheets | A video model, one clip per prompt, describing the same people again each time |
| Voices and dialogue | Lines are performed in the video itself, one voice per character, in any of 15 languages | A text-to-speech tool for each line, then a lip-sync pass on every clip |
| Fixing one shot | Edit that shot's text and regenerate the segment alone; the rest of the episode is untouched | Regenerate the clip, then re-cut the timeline |
| Finishing | Segments are composited into one episode file with its score; members download without the AI badge | A video editor to join the clips, add music and captions, then export |
| Publishing | You upload the finished episode to TikTok, YouTube, Instagram or anywhere else; nothing is posted for you | Upload by hand, the same as here |
Can you make money with AI dramas on TikTok and YouTube?
Yes, within each platform's rules, and the rules are about the account and the video, not about how the video was made. TikTok's Creator Rewards Program (checked November 2, 2026) is open to personal accounts aged 18+ in the United States, United Kingdom, Germany, Japan, South Korea, France, Mexico and Brazil with at least 10,000 followers and 100,000 video views in the last 30 days; a rewarded video must be original, longer than one minute and reach 1,000 views on the For You feed. YouTube's Partner Program needs 1,000 subscribers plus either 4,000 watch hours in the last 12 months or 10 million Shorts views in the last 90 days.
Both platforms require realistic AI-generated content to be labelled, and YouTube states that disclosing AI use alone does not limit a video's audience or its eligibility to earn. SceneMixer episodes are longer than a minute by design, carry an AI badge by default (members can switch it off and add the platform's own label instead), and are yours to publish. The full answer, with sources.
FAQ
Can AI turn a book into a movie?
Yes. Upload the text; it is read into acts or episodes, cast and rendered. Long books are split into volumes.
How long a book can I upload?
Up to 300,000 characters of English in one project; longer books in several projects.
Can I upload a PDF or EPUB?
No. Paste the text or export it to TXT or DOCX.
Can I adapt someone else's book?
Only with the rights. Public-domain texts are fine; famous characters from protected works are refused.
Will the characters look the same in volume two?
Yes, if you pick them from your library instead of generating new ones.
Can it keep the narrator?
Yes. Narration can be voice-over lines spoken by a narrator character.
Is SceneMixer like ReelShort or DramaBox?
No. ReelShort and DramaBox are apps for watching short dramas. SceneMixer is for making them: it turns your script or novel into episodes with a consistent cast and spoken dialogue, and you publish the episodes wherever you like, including those platforms' creator programmes where they exist.
Updated November 2, 2026