User Avatar

Business Analyst | Stroke Survivor | Digital Writer. Reviewing lessons from my recovery and career in manufacturing, finance & IT to discover processes improvements.

Can AI Image Generation and Text-to-Speech software be combined to Create Video Stories for Children?
John Tanner

There is an increased demand for short videos and especially educational content aimed at children.
I'm looking to test this out for some children at my wife's nursery. This will;

  • allow me to get familiar with the software and the production techniques needed to create short video stories.

  • provide me with a captive audience to get basic feedback.

Advanced text-to-speech (TTS) technology has transformed opportunity to create video stories. I'm going to use the Talking Photos platform by Paul Ponna, to making digital images come alive.

The Impact of Voice in Storytelling

Voice is so critical as it conveys emotions, personality, and tone.
Advanced TTS technology, allows the user to input a story and output realistic voiceovers immediately, without needing a voice actor.

Realistic Voiceovers

Modern TTS systems use AI algorithms to generate speech that mimics human intonation, rhythm, and inflection. Imagine a story featuring a playful rabbit. With TTS, the rabbit can have a high-pitched, cheerful voice that brings its personality to life, while a wise old turtle could have a deep, calm tone.

Customisation and Diversity

TTS allows customised voices according. Creators can choose accents, languages and tones. This helps in multicultural settings, where children benefit from hearing stories with familiar accents.

A well-narrated story will capture attention and guide them through the plot. The narration speed can be adjusted to emphasise key moments, building suspense or excitement at crucial points.
The Talking Pictures software has prompt input boxes which allow you to describe your character for AI to create, in 2D, 3D Disney Pixar style or from an uploaded picture.
Pairing AI generated images with text to speech software and functionality that makes the mouth move in time to the words should allow to ceate short Eduvcational videos for Nursey aged children to test if it improves their comprehension.

Conclusion

I'm looking forward to trialing the software to see if I can create educational material, specifically for nursery children that often don't have English as a first language and will share my findings.