
Neil Zeghidour is the co-founder and CEO of Gradium. Neil founded Gradium after a decade of building and leading frontier generative audio teams at Meta and Google DeepMind. Being frustrated by slow and brittle voice assistants , he built the engineering teams that developed the first neural audio codecs and introduced the first audio LLMs, such as AudioLM, at Google. He later created Kyutai to launch Moshi, the world's first real-time, full-duplex conversational AI , and Hibiki, the first simultaneous speech-to-speech translation system. Today, Gradium is focused on helping developers build natural, real-time voice agents by providing ultra-low latency streaming APIs that transition these breakthroughs from the research lab to production.
Neil Zeghidour is one of the world's leading researchers on audio language models, having co-created Moshi (a real-time full-duplex speech-to-speech model) at Kyutai and now serving as CEO of Gradium, a Paris-based voice AI startup pushing ultra-low-latency, on-device voice AI. His session offers rare insight from someone who has shipped cutting-edge voice AI research into production, bridging foundation model architecture and the hard engineering realities of real-time voice agents.
Voice AI: when is the "Her" moment? — Neil Zeghidour, Gradium AIAI Engineer · May 2026
Voice AI's Big Moment: Top Researcher on Why Everything Is Changing (Neil Zeghidour, Gradium AI)The MAD Podcast with Matt Turck · Feb 2026
Audio Language Models — Neil ZeghidourTTIC Summer Workshop on Foundations of Speech and Audio · Sep 2025
Gradium développe une IA générative audio : "On est les experts historiques de l'IA vocale"Dec 2025
On a testé le futur de l'IA Vocale avec Neil ZeghidourJan 2026Public activity researched automatically · as of Jun 2026