AI voice generation for teams
A voice your whole team can use.
Clone a voice from five seconds of audio. Generate up to 5,000 characters at a time. Every voice and every generation lives in your organization’s workspace — not locked to one account.
One line · Multiple system voices
“In a village tucked between mist-covered mountains, there lived an old clockmaker whose clocks never told the right time — but they always told the truth.”
From a voice memo to a finished read.
Upload a sample
Five seconds of clean audio is enough. Files up to 4 MB. The voice is created once and becomes available to everyone in the workspace.
Direct the read
Write up to 5,000 characters, then shape how much the delivery varies, how focused it stays and how its cadence moves — until it's the read you wanted.
Generate and keep it
Play it back on the waveform, download it, and find it again later. Full generation history is org-scoped, so nothing lives on one person's machine.
Chatterbox Turbo, running on A10G GPUs.
Six things teams do on day one.
These six sit in the workspace as quick actions, scripts already written. Pick one, pick a voice, and hear it.
Narrate a Story
Bring characters to life with expressive AI narration.
In a village tucked between mist-covered mountains, there lived an old clockmaker whose clocks never told the right time — but they always told the truth. One rainy evening, a stranger walked in and asked for a clock that could show him his future.
Introducing BrightBean Coffee — the smoothest roast you'll ever taste. Sourced from high-altitude farms, slow-roasted to perfection, and delivered fresh to your door every single week. Wake up to something extraordinary. Try BrightBean today and get your first bag free.
Record an Ad
Create professional advertisements with lifelike AI voices.
Direct a Movie Scene
Generate dramatic dialogue for film and video.
The rain hammered against the window as she turned to face him. You knew, didn't you? she whispered, her voice barely holding together. He stepped forward, jaw clenched. I did what I had to do. The silence between them was louder than the storm outside.
Voice a Game Character
Build immersive worlds with dynamic character voices.
Listen up, adventurer. The realm of Ashenvale is crumbling, and the Crystal of Eternity has been shattered into seven pieces. You are the only one who can reassemble it. Gather your courage, sharpen your blade, and meet me at the Gates of Dawn.
Introduce Your Podcast
Hook your listeners from the very first second.
Hey everyone, welcome back to another episode of The Curious Mind — the podcast where we dig into the stories, science, and strange ideas that shape our world. I'm your host, and today we have an incredible guest.
Guide a Meditation
Craft soothing, calming audio for wellness content.
Close your eyes and take a deep breath in. Hold it gently... and release. Feel the weight of the day slowly melting away. With each breath, you're sinking deeper into calm. Just here. Just now.
A library, not a list.
Resonance’s system voices sit alongside the ones your organization creates, filed under twelve categories so the right read is two clicks away.
The performance is yours to direct.
Most tools give you one voice and one reading of it. Resonance gives you four controls over how the line is actually delivered — and remembers every one of them per generation, so a take you liked can be run again exactly.
Try the controlsShape of the read at these settings
You pay for what you generate.
Two meters, billed separately: characters of speech, and voices you generate. No seats, no minimums.
Questions.
How much audio do I need to clone a voice?
Five seconds or more, in a file up to 4 MB. Cleaner input gives a cleaner voice, but you don't need a studio session.
Who can use a voice once it exists?
Everyone in the organization. Voices are org-scoped, not per-user, so one person's upload becomes the whole team's asset.
How long can one generation be?
Up to 5,000 characters at a time. Longer pieces are generated in sequence and kept together in history.
What control do I have over the output?
Creativity, Voice Variety, Expression Range and Natural Flow are all yours to set, and each one is stored with the generation so a good take can be reproduced.
What's running underneath?
Chatterbox Turbo on A10G GPUs. It's the reason a 5,000-character generation comes back in the time it takes to read the script.
How does billing work?
Two meters. A$0.50 per 1,000 characters of speech generated, and A$0.40 each time you generate a voice. There are no seat fees.
Can I find something I generated last month?
Yes. Every generation is kept in the workspace with its script, its voice and its settings, and plays back on the waveform.
Is there a public API?
Not yet. Resonance is used through the web workspace today.