Neil Zeghidour

Neil Zeghidour

Co-founder & CEO · Gradium

Share

Bio

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.

Sessions (5)

Additional Speaker Details

Using publicly available information we constructed an analysis to help you get a feel for this speaker before deciding to attend their session.

Zeghidour is a senior author behind a string of audio LLM / neural-codec systems (Moshi, Hibiki, and earlier SoundStream/AudioLM/MusicLM work) and now leads Gradium building real-time, on-device voice models. His AI Engineer talk pairs a clear vision for where conversational voice AI is heading (framed around the movie 'Her') with concrete latency/WER and speaker-similarity benchmarks for the Phonon TTS model and a live travel-agent voice-bot demo, arguing the cascaded STT-LLM-TTS stack is being replaced by full-duplex speech-to-speech. Attend for a research-grounded, production-oriented look at real-time voice AI.

Speaking style

Big-pictureDeeply technicalDemo-drivenBattle-tested

Recent talks (2)

GitHub

@lienz

Recent writing (5)

Podcasts & interviews (4)