Skip to content

text2video

Turn written text into a subtitled, voiced video

Visit official site

What text2video is

The tool is described as converting text into video automatically, an idea that started with visual reading of novels so written content can be read in a more vivid way. It supports free use and can be customised to individual needs.

What you can do with it

  • Split input text into segments
  • Generate images from the segments
  • Synthesise speech from the text
  • Overlay subtitles and assemble the final video

Application scenarios

  • Convert novel chapters into video automatically
  • Turn written news reports into playable video
  • Turn e-book content into video with narration

How it is built

  • stable-diffusion generates the images
  • edge-tts produces the speech
  • ffmpeg joins the material into a video with subtitles and narration

Pros & cons

✓ What we like

  • The stated goal is visual reading of novels
  • Individuals can customise the tool to their needs

! What to watch out for

  • Output depends on the separate image and speech generation steps
  • Video assembly relies on ffmpeg

FAQ

Which technologies are named?

The material names stable-diffusion, edge-tts and ffmpeg.

What was the original goal?

The material states it was built for visual reading of novels.

Is it free to use?

The material states the tool supports free use and customisation.

Last reviewed: 2026-11-15

More AI video generation tools

View all →

How we review