Gradium is a voice AI lab (Paris and Silicon Valley) building audio language models for real-time, low-latency Text-to-Speech, Speech-to-Text, and Speech-to-Speech translation. Founded in 2025 by ex-DeepMind / Meta / Kyutai researchers (Neil Zeghidour, Olivier Teboul, Laurent Mazaré, Alexandre Défossez), Gradium exposes a developer API over REST… - View it on GitHub