How to Create an Explainer Video in Video Studio

Turn one source into a narrated video

Video Studio takes a single source — text you paste or a document you upload — and plans it into editable scenes. You choose the narrator, review every scene, then generate the images and audio that become the final video.

Here is an example of what Video Studio produces:

1. Open Video Studio and choose a scenario

Click New video, or pick one of the four scenario cards on the Video Studio home page. Each card sets a starting point for how your content gets structured:

Scenario	Best for	Typical use
Training Video	Turn policies, procedures, and internal knowledge into clear learning scenes	Onboarding, compliance, SOPs
Product Explainer	Show the problem, workflow, benefits, and next step in a product-led story	Demos, feature launches, sales
Knowledge Explainer	Break a concept into visual chapters with concise, natural narration	Education, research, how-to
Custom Video	Describe the audience, structure, tone, and outcome you want from your content	Any format you define

2. Name the project

Project name is optional and limited to 120 characters. If you leave it blank, VocalVia still creates the project so you can start immediately.

3. Add your source material

Under Source type, choose how you want to provide the content:

Source	Limit	Notes
Paste text	20,000 characters	The counter turns red and Create scenes is disabled past the limit
Upload file	PDF, DOCX, TXT, or Markdown, up to 20 MB	PDFs may contain up to 50 pages

If you upload a PDF, choose PDF scene structure:

One scene per page — best for slides and training decks
Let AI organize — combines related pages

Long uploads are handled for you: files between 20,000 and 100,000 characters are summarized down automatically before planning, so you get a workable scene draft instead of a rejection.

4. Set narration language and detail

Narration language: Auto-detect from source, English, Chinese, Japanese, or Korean. With auto-detect on pasted text, VocalVia shows what it detected so you can override it.
Level of detail: Concise (key points), Balanced (clear and complete, the default), or Detailed (more explanation). This guides pacing rather than fixing a scene count.

5. Add video direction (optional)

Use Video direction to describe the audience, tone, focus, or must-cover points — up to 4,000 characters. VocalVia plans the scene count automatically from this.

6. Create the scenes

Click Create scenes. Processing runs in the background as a job, so you can leave the project and come back. While it works you will see stage text such as Analyze the source and Write editable scenes with a progress percentage. Completed batches save automatically.

If a document cannot be processed, you will see The document could not be processed. — retrying, or using a shorter file, usually resolves it.

7. Choose a narrator

In step Choose narration, pick a Narrator voice using Browse voices. One narrator is used for the whole video. You must select a voice before audio can be generated.

You can also add Background music and adjust Music volume — from -36 dB (quiet) to -8 dB (loud), with presets Light, Balanced (the default, -22 dB), and Present.

8. Review the scenes

In step Review scenes, edit each scene's Narration (up to 600 characters) and set its Delivery style: Neutral, Warm, Energetic, Authoritative, Calm, or Custom. With Custom you can write your own delivery direction, for example calm, reassuring, and measured.

You can reorder scenes with Move scene up and Move scene down, delete a scene, or add more with Insert scene and Add scene. Auto Tag All labels every scene in one click.

To control the look, expand Keep visuals consistent and choose a Consistency mode:

Mode	Effect
Independent scenes	Each scene is generated on its own
Consistent style	Scenes share a visual treatment
Character & scene consistency	Uses a reference image to keep characters and scenes stable

Describe the look in Visual style (for example Modern editorial illustration, warm neutral palette), and optionally upload a Reference character or scene image — JPEG, PNG, or WebP, up to 10 MB.

9. Generate images and audio

In step Generate video, generate assets in bulk or per scene:

Generate all images / Retry failed images
Generate all audio / Retry failed audio

Per scene you can Generate image or Generate new image, Upload image to use your own, Use original PDF page when working from a PDF, or write a Custom image prompt.

If you try to generate audio without a narrator, VocalVia will remind you: Choose a narrator voice before generating audio.

Turn on Add subtitles to burn the narration into the final video as captions.

10. Download the MP4

When rendering finishes, the video plays inline and a Download MP4 button appears. The file is MP4 / H.264, 1280×720 (720p), 30 fps, AAC 192 kbps.

Tip: Downloads are kept for 7 days, and the finish date is shown next to the button. After that you will see This video expired after 7 days. Generate it again to create a new download.

Limits to keep in mind

Limit	Value
Scenes per project	24 (50 when using one scene per page from a PDF)
Video renders per day	3
Simultaneous renders	1
Upload size	20 MB; PDFs up to 50 pages
Pasted text	20,000 characters

Troubleshooting

Message	What it means
`This source is too long to process. Please use a shorter document or file.`	Trim the source, or let an upload be summarized automatically
`This PDF has {n} pages. PDF uploads support up to {m} pages.`	Split the PDF, or use `Let AI organize`
`The uploaded document does not contain readable text.`	The file is likely a scan; use an OCR'd or text-based copy
`We could not identify the pages in this PDF. Try AI organization instead.`	Switch the PDF scene structure to `Let AI organize`
`The narrator voice could not be found. Choose a different voice and try again.`	Re-pick the narrator, then regenerate the affected audio
`We could not finish the scene draft. Your project and source are safe. Try again in a moment.`	Transient failure; your project is intact — retry

How to Create an Explainer Video in Video Studio

Put the guide into practice