NewIntroducing Phonon ・ Our first open, on-device TTS model
Spotlight post
Gradium Extends Funding to $100 Million and Expands to Silicon Valley
Gradium extends its seed funding to $100 million, welcoming new investors including NVIDIA, and opens a San Francisco Bay Area office to scale its real-time voice AI.
Models
Showcase
Latest post
How do you describe a voice? What we learned from designing 16,000 of them
To build the Gradium voice catalog, we designed more than 16,000 voices from written descriptions and kept about 1,400. Here is what that taught us about describing a voice: the five parts of a good prompt, which words the model hears reliably, and why the script does the acting, with samples you can play side by side.
Build
Company