Skip to main content

Create a Short Video from Text | MiOffice AI

Turn a scene description into a short MP4. Choose duration, framing, resolution and audio, then review the complete clip.

Input formats
Text and configured form inputs
Output options
MP4
Access
Sign-in required

Overview

Create a short video from a written scene description. Choose a 4s, 6s or 8s duration, landscape or portrait framing, a resolution and whether to request audio. The configured output is MP4. Keep your prompt focused on one scene, then watch the whole result before deciding whether to use it. This online workflow requires sign-in and an internet connection.

AI Text to Video generates a video from a text description and configured form inputs. Available controls configure the prompt, optional overlay text, duration, aspect ratio, resolution and audio. The configured output is MP4.

When to use

  • Use AI Text to Video when you want a short MP4 from a description of one scene, such as a sailboat crossing a lake or a gardener watering plants. You can choose the duration, aspect ratio, resolution and audio setting.
  • Choose it for a brief landscape or portrait scene that fits one of the available durations: 4s, 6s or 8s. A single main action gives you a clear point to check as you watch the full clip.

How to use

  1. Open AI Text to Video and use its linked workspace. Sign-in and an internet connection are required for this online workflow.

  2. In “Describe your video,” describe one scene in no more than 800 characters. Name the subject, action, setting and camera view. For example: “A red sailboat moving across a calm lake at dawn, viewed from the shore, soft mist over the water.” Keep the prompt focused on one main action rather than crowding a short clip with several events. Set “Duration” to 4s, 6s or 8s; choose “Aspect Ratio” 16:9 or 9:16; and select “Resolution” 720p, 1080p or 4k. Under “Audio,” choose whether to request audio. To include a short caption, put its exact wording in “Overlay text (optional)” and keep the scene description focused on what happens. Review the visible controls and restrictions before continuing.

  3. Click “Generate Video.” Watch the entire clip, checking the subject’s motion and appearance from first frame to last. If you requested audio or added overlay text, check those too, including every letter that must be exact. If a downloadable result is offered, verify the MP4 before using it. For a longer sequence, make separate clips, review each one, and edit them together afterward.

Settings reference

SettingOptionsDefault
Describe your videoTextEmpty
Overlay text (optional)TextEmpty
Duration4s: 4 seconds 6s: 6 seconds 8s: 8 seconds4s
Aspect Ratio16:9: Landscape 9:16: Portrait / Reels16:9
Resolution720p: 720p (HD) 1080p: 1080p (Full HD) 4k: 4K720p
Audiofalse: No audio true: Add audiofalse

Formats & limits

DetailRequirement
Input formatsText and configured form inputs
Output formatsMP4

Access & cost

DetailRequirement
Processing modeOnline processing requires sign-in and an internet connection.
Online processingSign-in required; Internet connection required

Examples & use cases

A creator preparing a brief opening visual.

A calm lake scene for a wide introduction

They want a simple dawn scene with one clear movement, not several actions crowded into a few seconds.

Text and configured form inputs to MP4

Describe your video:
A red sailboat moving across a calm lake at dawn, viewed from the shore, soft mist over the water.
Duration:
4s
Aspect Ratio:
16:9
Resolution:
720p
Audio:
false
  1. Keep the prompt centered on the sailboat’s movement and the lake setting, giving the clip one main action to review.
  2. Choose 16:9 for a landscape frame and 4s for a brief opening. Select 720p as the requested resolution and set Audio to No audio.
  3. Watch from the opening through the final frame. Check the boat’s movement and appearance before deciding whether the clip fits the introduction.

Expected outcome

If processing succeeds, the configured deliverable is an MP4. Review the complete scene before deciding whether to use it.

A creator planning a short vertical post.

A vertical clip with one garden action

They want a portrait-framed scene of a person watering plants, with one action to inspect rather than several scene changes.

Text and configured form inputs to MP4

Describe your video:
A gardener gently watering a row of green plants in a small garden, viewed at eye level.
Duration:
6s
Aspect Ratio:
9:16
Resolution:
1080p
Audio:
false
  1. Name the gardener, the watering action, the setting and the view to keep the description focused on one scene.
  2. Choose 9:16 for portrait framing and 6s for this scene. Select 1080p as the requested resolution and set Audio to No audio.
  3. Watch the full clip. Check the watering action and the gardener’s appearance throughout, then decide whether the framing suits the intended post.

Expected outcome

If processing succeeds, the configured deliverable is an MP4. Review the complete result before using it for the post.

A presenter preparing a quiet visual to accompany a talk.

A quiet mountain scene without audio

They want one gradual movement (a hiker walking along a trail) instead of a busy montage, and want to request a clip without audio.

Text and configured form inputs to MP4

Describe your video:
A lone hiker walking slowly along a mountain trail at sunrise, wide view of the valley.
Duration:
8s
Aspect Ratio:
16:9
Resolution:
1080p
Audio:
false
  1. Focus the description on the hiker’s single action and the trail setting so you can review that movement through the clip.
  2. Choose 8s for the longest available duration, 16:9 for a wide frame and No audio under Audio for a silent request. Select 1080p as the requested resolution.
  3. Watch from beginning to end. Check the hiker’s motion and appearance, and decide whether the result suits the talk.

Expected outcome

If processing succeeds, the configured deliverable is an MP4 with Audio set to No audio. Review the whole scene before using it.

More ways to use it

  • A creator developing a visual concept.: They have an idea for a paper kite rising over a hill but no source image; the configured inputs are text and form controls. If processing succeeds, the configured result is an MP4. Review the full clip to judge whether the kite’s movement and appearance fit the concept. Describe your video: A paper kite lifting into a light breeze above a grassy hill., Duration: 4s, Aspect Ratio: 16:9, Resolution: 720p, Audio: false.
  • A creator planning a vertical short-form scene.: They want a brief portrait-framed scene of a cyclist passing through a park, with one action to check throughout. If processing succeeds, the configured result is an MP4. Check the cyclist’s motion and appearance across the full clip and decide whether the portrait framing suits the intended post. Describe your video: A cyclist riding past a row of trees in a quiet park, viewed from the path., Duration: 6s, Aspect Ratio: 9:16, Resolution: 1080p, Audio: false.

Troubleshooting

The description includes several actions or details, making it hard to know what the short scene should focus on.

Try this: Simplify “Describe your video” to one subject, one action, a setting and a camera view.

What to expect: The next generation is configured around one scene. Watch the entire result to judge whether it is easier to follow.

You want to request audio, but “Audio” is set to “No audio.”

Try this: Choose “Add audio” under “Audio,” then review the generated result.

What to expect: The generation is configured to request audio. Check the full MP4 to decide whether the result meets your needs.

Privacy

Online processing uploads files. Completed results may remain available for later download. See Privacy Policy for current file-handling and retention details. Check the processing mode before starting.

Frequently asked questions

Can AI generate a video from text?

Yes. AI Text to Video generates a video from a text description and configured form inputs. Its configured output format is MP4.

Do I need to upload a photo?

No. The configured inputs are text and form controls, so you can start by describing the scene you want.

Can I make the clip without sound?

Yes. Under “Audio,” choose “No audio.” The configured output is MP4; review the result to check that it suits your needs.

Why do objects change appearance during an AI-generated video?

Generated motion can introduce inconsistencies between frames, such as changing objects, distorted hands or unstable text. Keep the prompt focused on one simple scene and watch the whole clip; a convincing opening frame doesn’t show whether the rest is consistent.

What should I include in a text-to-video prompt?

Describe one scene and name the subject, action, setting and camera view. For example: “A red sailboat moving across a calm lake at dawn, viewed from the shore, soft mist over the water.” Keep the request within 800 characters and focused on one main action, then inspect the full clip.

How long can the generated clip be?

The “Duration” choices are 4s, 6s and 8s. For a longer sequence, make separate clips, review each one and edit them together afterward.

Can I choose landscape or portrait framing?

Yes. “Aspect Ratio” offers 16:9 (Landscape) and 9:16 (Portrait / Reels). Choose the framing for your intended use, then review the generated clip.

What resolution choices are available?

“Resolution” offers 720p, 1080p and 4k. Select a value before generation and inspect the resulting MP4.

What format does the tool generate?

The configured output format is MP4. If a downloadable file is offered, verify it before using it.

Can I control the visual style or camera movement?

You can describe a camera view in “Describe your video.” The listed controls don’t include a separate style or camera-movement control, so describe the view you want and inspect the generated clip rather than assuming a particular result.

Can I turn a blog post or long script into a full video automatically?

The documented workflow uses a prompt to describe one scene, and the available durations are 4s, 6s and 8s. Automatic conversion of a full article or long script into a sequence isn’t specified.

Can I generate videos in multiple languages with subtitles?

The listed controls include “Audio” and “Overlay text (optional),” but don’t specify language selection or automatic subtitles. You can enter a short caption in the overlay field and check its wording in the clip.

Does the tool add a caption automatically?

The “Overlay text (optional)” control lets you enter short text for the clip. Automatic caption generation isn’t specified; check the wording in the result, including every letter that must be exact.

What happens to files and generated results?

Online processing uploads files. Completed results may remain available for later download. See Privacy Policy for current file-handling and retention details. Check the processing mode before starting.