Unit IV · Presentations with AI
18. Adding audio, video, animation and music
A presentation with only text is boring. Multimedia means using images, audio, video, animation and music together. This chapter shows how to add each one with AI tools. This covers Lab experiments 15 and 16.
1. Images
You already know this from Chapter 11. Ask Gemini, ChatGPT or Canva Magic Media for an image. Say "no text" and the style. Insert it into the slide.
For diagrams, ask: "Draw a simple labelled diagram of a four-stroke engine, flat style, white background."
2. Audio (narration)
Narration is a voice that explains the slide. You can record your own voice, or let AI speak.
Record yourself: In Canva, click Record yourself under Uploads. In PowerPoint, use Insert → Audio → Record. Your phone's voice recorder also works.
AI voice (text-to-speech):
- Write the script with Gemini: "Write a 40-second narration for this slide in simple English."
- Turn text into speech with ElevenLabs (free plan), Google Cloud TTS demo or NaturalReader.
- NotebookLM's Audio Overview can also make a two-person discussion from your notes.
- Download the MP3. Insert it into the slide.
3. Video
Insert an existing video: In Google Slides, Insert → Video lets you paste a YouTube link. In PowerPoint, Insert → Video. In Canva, drag a video from Elements or Uploads.
Make a short AI video:
- Gemini can make short video clips from a text prompt (with Veo), on supported plans.
- Google Vids makes a full video from a prompt or a document.
- Canva Magic Media can make short clips.
- Pika, Runway, Luma — free plans with limits.
Keep videos short: 10 to 30 seconds per slide.
4. Animation and transitions
Animation moves things on one slide. A transition is the effect between two slides.
- Google Slides: Select an object → Insert → Animation. Choose "Fade in", "Fly in", "Appear". Set "On click" or "After previous". For transitions, Slide → Transition.
- PowerPoint: Animations tab and Transitions tab.
- Canva: Click an object → Animate. For the whole page, click the page → Animate.
- Gamma: Animations are automatic; you can turn them on or off in the theme.
Rule: use one transition for the whole deck. Too many effects look childish.
5. Background music
- Free music: Pixabay Music, YouTube Audio Library (under Audio Library), Free Music Archive.
- AI-made music: Suno, Udio, MusicFX by Google. Prompt: "Calm instrumental background music, 1 minute, no vocals."
- In Canva: Elements → Audio. Drag onto the timeline. It plays across all pages.
- In PowerPoint: insert the audio on slide 1, then tick Play across slides and Loop.
- Keep the volume low. The narration must be louder than the music.
Putting it together (the easy way)
Canva is the easiest tool for all of this in one place.
- Make the slides in Gamma or Gemini + Google Slides. Export as PPTX.
- Open Canva → Create a design → Presentation → Upload the PPTX (or import from PowerPoint).
- Add animation, narration, a video and music as above.
- Share → Download → MP4 Video to get a video file. Or Present from Canva.
Check the licence
Always use images, music and videos that are free to use. Pixabay, Pexels, Unsplash and the YouTube Audio Library are safe. Never take music from a film or a song from YouTube; that is copyright violation. AI-generated content is fine for college work, but check each tool's rules before using it commercially.
Try it
- Take the deck you made in Chapter 16 or 17. Add one AI image, one narration (your voice or AI voice), and one short video.
- Add animations to the text on 3 slides and one transition for the whole deck.
- Add a background music track from Pixabay. Export the whole thing as an MP4 from Canva.
- Play the MP4 on your phone. Is the narration clear? Is the music too loud?
New words
- Multimedia — many types of media together: text, image, audio, video.
- Narration — a voice that speaks over the slides.
- Text-to-speech (TTS) — turning written text into a spoken voice.
- MP3 — a common audio file format.
- Transition — the effect when moving from one slide to the next.
- Timeline — the bar at the bottom of a video editor showing time.
- Loop — to play again and again.
- Instrumental — music with no singing.
- Licence — permission to use something; "free to use" means the licence allows it.
- Commercial — for business, to make money.