Scene-by-scene timeline & spoken transcript
The Hook
The Creator's Objective
“I need to make a promo video for our new text to speech model. Let's start with a voiceover.”
- On screen
- Sequences shortened and screen images simulated. Results for illustrative purposes.
- Camera
- Static eye-level front shot of talent seated at desk with laptop.
- Motion
- Live-action framing paired with subtle conversational delivery.
Feature Teaser
Prompting First Voiceover
“Introducing text to speech.”
- On screen
- Booming, animated a...
- Camera
- Close-up over hands typing on keyboard, cutting to talent reacting.
- Motion
- Text-type kinetic overlay syncing with mechanical typing.
Product Reveal
Voice Design via Prompt
“No, more like this. Introducing... da da da da... text to speech. Transforms simple prompts into consistent expressive voice outputs on demand.”
- On screen
- Create voice · Voice Design Describe it Woman in her 30's, pumped, emphatic with Brooklyn accent Option 1 Ready to play Option 2 Ready to play Option 3 Ready to play Gemini Audio Promo Narrator is ready Use it in the Text to speech composer, or create another voice. Use voice | Create another voice
- Camera
- Clean 2D screen UI presentation with soft floating elevation.
- Motion
- Micro-interaction card expansions and animated waveform icons.
Feature Teaser
Browsing Voice Library
“Okay, now let's add in another voice for this dialogue scene in the script. Or choose from over a thousand ready-to-go voices.”
- On screen
- Explore voices Browse Voice Library The Mad Scientist The Meditation Guide The Hype Announcer The Ad Voiceover The Late-Night DJ The Cheeky Sidekick
- Camera
- Overhead top-down planar camera looking down at workspace.
- Motion
- Horizontal carousel UI track tracking over physical desk surface.
Feature Teaser
Remixing Voice Pitch
“Okay, but what if we had that voice a little bit deeper? And change it however you want.”
- On screen
- Remix it Make this voice a little bit deeper Pick your voice remix Deep Voice 1 Deeper Voice 2 Deepest Voice 3 Voice remix coming soon.
- Camera
- Medium side-angle shot of talent with floating modal window overlay.
- Motion
- Pop-in modal animation with list option selection transition.
Feature Teaser
Multi-Speaker Audio Composition
“Okay, perfect. Now let's drop these voices into the dialogue scene. You can pick and drop your favorite saved voices. And you can direct (uh-huh) them in a multi-speaker scene.”
- On screen
- Female Bespoke Voice: You can pick and drop your favourite saved voices Male Deeper Voice: And you can direct [uh-huh] them Female Bespoke Voice: In a multi-speaker scene!
- Camera
- Horizontal pan across animated audio waveforms on pastel gradient.
- Motion
- Dynamic audio waveform bars reacting in amplitude to dialogue bubbles.
Product Reveal
Voice Replication & Verification
“Actually, maybe it should be my voice. The lighthouse keeper watched the silver horizon as the morning fog slowly lifted across... Or recreate your own voice, safely protected by a quick verbal identity check.”
- On screen
- Create voice · Voice Replication 1 - Add a voice sample 2 - Verify it's you Ready for verification... Your replicated voice is ready Name your custom voice to save it to your library and use it for speech generation. Luke's voice- 1 Use voice
- Camera
- Macro profile close-up on studio microphone and talent recording.
- Motion
- Real-time recording meter pulses followed by confirmation modal.
Call to Action
Brand Lockup & Climax
“Give your words a voice with Gemini Audio.”
- On screen
- Give your words a voice Gemini Audio
- Camera
- Overhead top-down desk shot pulling out slightly.
- Motion
- Staggered typography reveal paired with animated 4-color Gemini sparkle icon.
Motion design primitives
Synthesizable in Remotion · key components of the ai-audio-workflow-showcase template.
WaveformSpectrumBars
Rounded vertical bars modulate height smoothly based on simulated voice amplitude against a gradient canvas.
+ Code construction recipe
Generate an array of 40 rounded div elements; map heights using Remotion spring interpolated with sine oscillations scaled by scene frame.
FloatingGlassDialogCard
Rounded white translucent cards with soft dropshadows slide up and stack neatly in conversation flow.
+ Code construction recipe
Use interpolate on translateY (30 to 0px) and opacity (0 to 1) with spring damping: 15, mass: 0.8.
CarouselTrayOverlay
Horizontal row of presets slides left across the screen over live video footage with smooth momentum easing.
+ Code construction recipe
Parent flex container translated on X-axis using interpolate based on video frame timeline.
Style DNA & aesthetic system
Visual aesthetic
Typography
Motion
Special effects
Pacing & rhythm
Conceptual story rhythm
- 1
Setup Hook
Purpose. Establish creator intent to produce speech audio.
Execution. Direct-to-camera desk shot cut with keyboard typing.
- 2
Prompt & Generate
Purpose. Demonstrate intuitive natural language voice generation.
Execution. Prompt card typing animation and synthesized playback.
- 3
Explore & Tweak
Purpose. Show library depth and nuance controls like pitch remixing.
Execution. Horizontal voice card slider overlaid on desk footage.
- 4
Dialogue Integration
Purpose. Showcase complex multi-voice script orchestration.
Execution. Soundwave canvas with conversational speech tags.
- 5
Voice Replication
Purpose. Highlight proprietary voice cloning and security verification.
Execution. Studio mic live capture and immediate AI generation.
- 6
Call to Action
Purpose. Brand reinforcement and tagline delivery.
Execution. Overhead desk shot with crisp typography and Gemini logo.
Remix in Animatiq Studio
Master remix prompt · agent-ready
Sample remix
Objective
Announcing an AI podcast editing tool with instant voice dubbing and cleanup.How the recipe adapts
The creator starts by editing a podcast episode, filters noisy room audio via prompt, chooses dubbed host accents from the carousel, and replicates co-host voices instantly.Remix blueprint · ai-audio-workflow-showcase
Scene durations (8 scenes, 60s)
Key Remotion components
Related AI Agents Startup Launches
Explore all 1064 AI Agents launches →
To ensure that artificial general intelligence benefits all of humanity
Introducing Claude Fable 5: a Mythos-class model that we’ve made safe for general use. Its capabilities exceed those of any model we’ve ever made generally available. https://t.co/2AvmEjHIX8
To understand the true nature of the universe.