The Future of Voice AI is Here: Real-Time Cloning, On-Device & Live Translation (Gradium CEO)

The MAD Podcast with Matt Turck · Intermediate ·🧠 Large Language Models ·2w ago
Current voice AI is too slow and expensive for interactive applications like gaming and robotics. Enter Gradium, a commercial spin-off from the Kyutai AI lab. In this demo, Neil Zeghidour showcases their real-time voice infrastructure. Watch their killer features in action: a high-fidelity text-to-speech model running entirely on a CPU, interactive voice agents that maintain natural conversation flow, and real-time speech translation with voice cloning. They even demonstrate restoring the voice of ALS patient Olivier Goy 00:31 - The backstory: A commercial spin-off from Kyutai Labs. 01:16 - The shift from offline to interactive voice in gaming and live streams. 03:12 - Live demo: AI-generated personalized esports commentary. 04:33 - Restoring the voice of ALS patient Olivier Goy. 05:16 - Creating real-time personalized videos. 06:41 - Running a 100M parameter text-to-speech model locally on a CPU. 08:41 - Building interactive voice agents that use function calling. 11:47 - Hibiki: Real-time, on-device speech-to-speech translation. Gradium Website - @ X/Twitter - @AI HOSTED BY: FirstMark Capital Website - @ X/Twitter - @rkCap Matt Turck (Managing Director) Blog - @ LinkedIn - @k/ X/Twitter - @ck This session was recorded live at a recent Data Driven NYC, our in-person, monthly event series. If you are ever in New York, you can join the upcoming events by following FirstMark on Luma: @rkcap Check out the MAD Podcast: Spotify - @LATDSaFvgJG80ACcRJtq Apple - https://podcasts.apple.com/us/podcast/the-mad-podcast-with-matt-turck/id1686238724
Watch on YouTube ↗ (saves to browser)
Sign in to unlock AI tutor explanation · ⚡30

Related AI Lessons

⚡
Gemma 4 + LiteRTLM 0.11.0: Finally, On-Device AI Feels Fast (and Stable) on Qualcomm Devices
Learn how Gemma 4 and LiteRTLM 0.11.0 enable fast and stable on-device AI on Qualcomm devices, revolutionizing the user experience
Medium · LLM
 ⚡
What's new in Prompt Optimizer: latest features and improvements
Learn how to optimize prompts with the latest features and improvements in Prompt Optimizer, a crucial tool for effective LLM interactions
Dev.to AI
 ⚡
AI vs LLM vs AI Agents vs Automation — What’s the Real Difference?
Understand the differences between AI, LLM, AI Agents, and Automation to clarify their roles in technology
Dev.to AI
 ⚡
Why Python Became the Default Language for AI?
Discover why Python became the go-to language for AI despite not being the fastest or most powerful, and how its versatility and ease of use contributed to its dominance
Dev.to · Sanket Parmar

Chapters (8)

0:31 The backstory: A commercial spin-off from Kyutai Labs.
1:16 The shift from offline to interactive voice in gaming and live streams.
3:12 Live demo: AI-generated personalized esports commentary.
4:33 Restoring the voice of ALS patient Olivier Goy.
5:16 Creating real-time personalized videos.
6:41 Running a 100M parameter text-to-speech model locally on a CPU.
8:41 Building interactive voice agents that use function calling.
11:47 Hibiki: Real-time, on-device speech-to-speech translation.
Up next
5 Levels of AI Agents - From Simple LLM Calls to Multi-Agent Systems
Dave Ebbelaar (LLM Eng)
Watch →