Voiceovers 2.0
Add lifelike AI narration to any demo with Voiceovers 2.0. Choose a voice, turn on expressive mode, clone your own voice, fix pronunciation, or record and upload manual audio.
What is Voiceovers 2.0?
Voiceovers 2.0 brings a refreshed editing sidebar, new voices grouped by locale and region, a quick link to the Pronunciation Library, and a brand new expressive mode with emotions, whispers, and tone. Add AI narration, clone your own voice, or record manual audio — all without a single video editing tool.
Before you start
You'll need:
A Supademo open in edit mode
A quiet space to record a short sample (only if you plan to clone your voice)
1. Set up AI voiceover
Open the Voiceover menu to add narration to your demo.
Open the voice dropdown to browse Supademo's AI voices.
Pick a voice — here we choose Bria, a warm American narrator.
Click Sync all to turn your hotspot text into narration automatically, or type custom narration per step.
Click Sync voiceovers to apply narration across every step.
Open Voice settings to fine-tune how the voice sounds.
Turn on Expressive mode so the voice acts out tone and emphasis.
Click Done to save your speed and stability settings.
Click Save to lock in your voiceover changes.
💡 Tip: Expressive mode reads your punctuation as cues — periods, exclamation marks, and spacing all shift the delivery. Tweak your script to dial in the right tone.
2. Clone your voice
Click Clone voice to create narration in your own voice.
Hit Record to start capturing your voice sample.
Read the on-screen script aloud so Supademo can model your voice.
Click Stop when you've finished reading.
3. Pronunciation Library
Open the Pronunciation Library to control how tricky words are said.
Type the word that's being mispronounced.
Enter the word as it's written.
Enter how it should sound, spelled phonetically (e.g. Supa-demo).
Click Add to save the pronunciation rule.
Preview, toggle, or delete any entry here.
Click Done to save your Pronunciation Library.
💡 Tip: Use the Pronunciation Library for product names and acronyms so they sound right across every voiceover, without editing each script.
4. Record or upload a manual voiceover
Choose Record my voice to narrate a step yourself.
Click Record voice to start your manual recording.
Click Stop to finish recording.
Prefer a file? Click Upload voice to add your own audio.
Click Save to apply your manual voiceover.
Confirm with Proceed with changes to publish your narration.
Want to generate voiceovers or edit voiceover text programmatically with AI? Try using the Supademo MCP.
Benefits
Lifelike narration — Expressive mode adds emotion, whispers, and tone so demos sound like a real person, not flat text-to-speech.
Your own voice — Clone your voice once and generate narration in it across every demo.
Consistent pronunciation — The Pronunciation Library keeps product names and acronyms sounding right everywhere.
Full flexibility — Mix AI voices, cloned voices, and manual recordings within the same Supademo.
Faster workflow — A refreshed sidebar with voices grouped by locale and region makes editing quick and intuitive.
Use Cases
Product Onboarding and Walkthroughs
Guide new users through your product with warm, natural narration that explains each step. Expressive mode keeps longer walkthroughs engaging instead of monotone.
Sales Demos and Leave-Behinds
Narrate demos in your own cloned voice so prospects hear a familiar, personal touch — even in async follow-ups and leave-behinds shared internally.
Multi-language and Accessibility
Generate narration in multiple languages and enable closed captions to make demos accessible to a wider, global audience.
Marketing and Website Embeds
Add polished, on-brand narration to embedded demos so website visitors get a guided experience without needing to read every annotation.
✨ The Result: Studio-quality narration in minutes — expressive, on-brand, and even in your own voice — without ever opening a video editor.
Last updated
Was this helpful?