Neil Zeghidour
CEO
Gradium
@neilzeghNeil 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)
Everyone says cascaded voice pipelines are dead and native speech models are the future. Yet production environments are still dominated by STT-LLM-TTS stacks. Reconciling the natural flow of native audio with the elite reasoning of a cascaded agent remains an unsolved systems problem. This talk dissects the brutal technical trade-offs behind that counterintuitive reality. We will break down why your voice agent is still stuck behaving like a walkie-talkie and map out the specific technical roadmap required to build full-duplex AI that actually works.
Walk out of this workshop with a deployed digital clone that makes your phone calls for you. We will skip the theory and immediately get our hands dirty wiring together OpenClaw, Twilio, and Gradium to build an autonomous voice agent on a live cellular network. You will tackle the hardest parts of real-time telephony: routing audio streams, handling human interruption, and killing latency. In 60 minutes, your AI will be ready to call restaurants for the daily special, book appointments, and actively negotiate on your behalf.
Walk out of this workshop with a deployed digital clone that makes your phone calls for you. We will skip the theory and immediately get our hands dirty wiring together OpenClaw, Twilio, and Gradium to build an autonomous voice agent on a live cellular network. You will tackle the hardest parts of real-time telephony: routing audio streams, handling human interruption, and killing latency. In 60 minutes, your AI will be ready to call restaurants for the daily special, book appointments, and actively negotiate on your behalf.
Walk out of this workshop with a deployed digital clone that makes your phone calls for you. We will skip the theory and immediately get our hands dirty wiring together OpenClaw, Twilio, and Gradium to build an autonomous voice agent on a live cellular network. You will tackle the hardest parts of real-time telephony: routing audio streams, handling human interruption, and killing latency. In 60 minutes, your AI will be ready to call restaurants for the daily special, book appointments, and actively negotiate on your behalf.
Language models give us the ability to create natural language, conversational, interfaces for computers. We are seeing a rapid shift among early adopters to using general language instead of traditional user interfaces for tasks like writing code and editing spreadsheets. Join the cofounders of Pipecat, Gradium, and Daily as we discuss the future of realtime voice and AI interfaces. Voice is the most efficient input mode for natural-language systems, and often the most efficient output mode, as well. But good voice interfaces require a very high degree of conversational facility, intelligence, task-specific reliability, and robustness to real-world realities like multiple speakers and background noise. There's a long history of voice interfaces in science fiction: Star Trek, Iron Man, Her. We'll use these depictions of computing possibilities as a jumping off point for talking about the ideal voice interface. How close are we to being able to build these interfaces with today's models, hardware, orchestration tooling, and UI libraries? What are the most promising research directions? What did the movies get wrong, now that we actually have experience building natural language, open-ended, voice systems? Speakers: Kwindla Kramer — Daily; Neil Zeghidour — Gradium.