Gradium
Gradium builds AI speech models optimized for voice agents: robust pronunciation delivered by natural, expressive, real-time voices, at scale.
Publisher details
✕
Gradium builds the AI speech models and infrastructure to power natural, expressive, real-time voice interactions at scale. Our models include Text-to-Speech, Speech-to-Text, Speech-to-Speech Translation, Voice cloning. Founded by a research team from Meta, Google Brain, Google DeepMind, Jane Street and Kyutai, Gradium builds on a decade of research in AI and voice to capture rhythm, register, and cultural nuance across multiple languages. gradium.ai
