Skip to content

IntermediateLesson 3 of 69 min read

Video and voice: the studio in your browser

A course from the Academy: Creating with AI: images, videos and ideas

Go to the quiz ↓

AI-generated video has covered in two years the ground that images took five to cover. Here's how to make the most of it right now, without hardware or budget.

The principle: from image to motion

The most reliable method today: start from an image. First, you generate a perfect image (previous lesson), then you ask a video tool to animate it by describing the motion: "the camera moves forward slowly, clouds drift by, waves move gently". You get a few seconds of footage.

Pro tip: for a looping animated background (website, home screen), give the same image as both the starting point AND the end point, with slow motion. The loop becomes invisible. This is exactly how Alyriaz's animated backgrounds are made.

Describing motion that works

  • One main motion per shot: the camera OR the subject, rarely both.
  • Slow beats fast: slow movements are more realistic and hide flaws.
  • Static camera by default: specify "static camera" if you just want the scene to feel alive.

Voice: reading your scripts aloud

Current synthetic voices are impressive: natural, expressive, available in every language. Typical use: write a script with AI, have a synthetic voice read it, assemble it over your images. A complete video, on your own.

The red line: cloning a real person's voice without their written consent is prohibited and can lead to legal action (right to image and voice). Generic synthetic voices, on the other hand, are free to use.

Analogy. Before, making a film required a team: camera operator, lighting technician, voice-over actor, editor. AI tools are that team, available on demand. But as on a real set, it's the director who makes the film: without a clear plan, even the most talented team shoots soulless footage.

Key takeaways

  • Reliable method: perfect image first, animation second.
  • Perfect loop: same image at start and end, slow motion.
  • One motion per shot, preferably slow.
  • Cloning a real voice without written consent: prohibited.

Key concepts

Complete the lesson

A 4-question quiz: 3 correct answers are enough, plus an exercise to practise. It opens in the Academy, on this same lesson.

Take the quiz and complete the lesson Free. With an account, your progress is saved and leads to the course certificate.

The course: Creating with AI: images, videos and ideas

  1. AI creation: the big picture8 min
  2. Generating images that match your idea.9 min
  3. Video and voice: the studio in your browser9 min
  4. Writing with AI without losing your voice8 min
  5. Who owns what you create?8 min
  6. Your first creative project from A to Z9 min

The whole Academy →The AI glossary