VAYESSA1. Structure the script scene by scene
Unlike a rhythmic photo montage, an explainer video is led by the spoken script and visual clarity. Keep each slide focused on a single idea—typically 5 to 8 seconds per scene: an opening problem or hook, two to four clear steps, and a closing call to action.
You will need Vayessa with a Studio license for MCP control and an ElevenLabs key added in the app if you want generated AI voice-over. Choose your target aspect ratio first (16:9 for landscape presentations and YouTube, or 9:16 for vertical social explainers).
Inspect my current Vayessa project first. Help me plan a 45-second 16:9 explainer video in 6 slides: 1) Hook, 2) The problem, 3) Step 1, 4) Step 2, 5) Step 3, and 6) Closing summary. Write concise slide narration for each slide and show me the storyboard before changing the project.
2. Gather stock B-roll, icons, and music responsibly
You can combine your own product recordings with royalty-free stock photos, transparent PNG illustrations, video clips, and background music from sources such as Pixabay. Download the files you want to use into a dedicated local project folder on your Mac before importing them into Vayessa.
| Asset type | How to use it in Vayessa | Licensing & attribution best practices |
|---|---|---|
Video clips (.mp4, .mov) | Add as main B-roll slides with add_photos and mute original clip audio (mute: true) so narration stays clear. | Allowed for commercial and personal explainers when combined into a multi-slide story. Never re-export a single unmodified stock clip on its own for resale. |
| Transparent PNGs & vectors | Place over slides as visual callouts or stickers using add_layer (type: "image") or frame with shape masks. | Avoid clips or illustrations showing real third-party brand logos or identifiable people in a way that implies endorsement. |
Background music & SFX (.mp3, .wav) | Set the bed track with set_music (timing: "none") and add sound effects on the timeline with add_audio. | When downloading music from Pixabay, save the free Audio License Certificate alongside your project to quickly clear any automated YouTube Content ID claims. |
Although the Pixabay Content License does not require on-screen credit for commercial or non-commercial videos, keeping a simple CREDITS.txt file in your project folder (recording the creator name, source URL, and download date) gives you a clean audit trail for clients and publishing platforms.
3. Let slide narration drive the timing
Import your local B-roll clips and background images into Vayessa, mute any distracting ambient video sound, and assign each scene’s spoken script to its slide narration field. Then generate the voice-over per slide so Vayessa automatically lengthens any slide that is shorter than its spoken line.
Add the media from /Users/your-name/Movies/Explainer/assets in storyboard order. Mute the audio on video slides, set the approved narration on each slide, and generate per-slide voice-over using my default voice with captions enabled, lengthen_slides on, and music ducking set to 0.25.
In MCP, generate_voiceover with per_slide: true, lengthen_slides: true, and duck_music: true aligns each voice clip to its slide and automatically lowers the background music while the narrator speaks.
4. Add step callouts and motion layers
Reinforce what the narrator is saying with clean on-screen graphics. Use Vayessa’s built-in motion templates (such as lower thirds, step headers, or call-to-action cards) with apply_motion_template, or build custom animated text, shape badges, and transparent PNG layers with add_layer.
On slides 3, 4, and 5, add a clean step badge and a short headline layer anchored to the bottom-left with a rise enter animation and word stagger. Make sure no layer covers faces or goes outside the safe area, then preview each slide.
Every layer call in Vayessa checks for safe-area margins, overlapping graphics, and covered faces. Review the returned warnings and inspect actual frames with preview before moving on.
5. Add optional credits and export
Set your background music track with set_music using timing: "none" so your carefully paced narration timing stays intact. If you want to credit stock creators or display your brand details at the end, add a closing card or subtle attribution line on the final slide.
Add /Users/your-name/Movies/Explainer/music/calm-bed.mp3 with timing set to none so slide lengths follow the voice-over. Preview the opening, middle step, and closing card, then wait for my approval before exporting to 1080p MP4.
Watch the exported video from start to finish to verify that voice ducking, caption readability, and slide transitions feel natural together, and store your exported video alongside your project’s stock license certificates.