Voice for every way you create and build.
Introducing BlueBell — World's #1 Voice Design Model
Characters
A friendly immigrant shopkeeper in his 50s. The voice is a warm, bouncy baritone with a rapid, staccato rhythm. It is high-energy, persuasive, and characterized by breathless bursts of entrepreneurial hustle.
"Hey boss! Good to see you. Just unpacked the new stuff."
Build for every voice flow
From creation to integration and scale, adapt to how you work
Design and shape a voice any way you want
From Voice Clone to Voice Design
Clone a voice from a short sample, then reshape it — accent, age, mood, energy. Start from reality or start from scratch; either way, no voice is ever locked in.
Speaks how you describe
Describe the performance — emotion, pace, breath, texture — and the model interprets every nuance. You direct, it performs; no parameter tuning, no post-editing required.
Voice that feels alive
Bring voices to life with depth, nuance, and emotion. From subtle inflections to expressive delivery, create voices that feel human, engaging, and full of character.
Find the right voice for your project, and make it your own
Explore Voice LibraryBuild voice products with Breeze API
Build with the Breeze Developer API. Manage keys, monitor API usage, and reuse saved voices across Studio and API workflows.
Clone and use a voice
Clone a voice from a reference audio sample and use it across your projects. Maintain consistency while adapting it to different scenarios.
Design a voice
Design a voice from scratch using a text prompt. Define the character, style, and qualities without recording any audio.
Direct a performance
Direct a performance by describing how the voice should sound. Control tone, emotion, and delivery to shape each line.
The new frontier of voice design
Bluebell sets a new bar on InstructTTSEval, leading top production TTS systems in instruction following.
Average scores across all benchmarks shown here.
Latest Updates
Stay up to date with our latest work, research, and collaborations.
