Zeghidour: End-to-end speech models have massive switching costs for upgrades
Neil Zeghidour · Voice AI’s Big Moment: Top Researcher on Why Everything Is Changing (Neil Zeghidour, Gradium AI) · Feb 19, 2026 · at 52:50
Neil Zeghidour, AI researcher and CEO of Gradium AI, outlines the trade-offs between integrated speech-to-speech models and modular cascaded systems.
0:00 / 0:16exact quote · 16.3s
▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark
“One drawback of speech-to-speech models is that since everything is integrated, when you go from a text model to the speech-to-speech model, you need to fine-tune it on speech data. So now it's the cost to switch the underlying text model is extremely high because you will need to re-finetune everything from scratch.”
quote is from the automated transcript, cleaned for reading: filler sounds and stutters are removed, nothing is rephrased. names can be misheard (the analysis reads context, assessments check outside sources). how →
More from Neil Zeghidour
Zeghidour: Chinese open research forces Western competitors to publish
“And they also, you know, like the Chinese lab, I, I'm making a remarkable work, and it's a kind of, are forcing everyone to stay open to some extent because otherwise it also hurts the ego, I think, of the people who are in the labs that don't publish.”
Zeghidour: Zero progress made on noisy multi-speaker understanding in 10 years
“In TTS, we see a lot of progress. For this kind of hard understanding problem, I hear people saying the exact same stuff as they did 10 years ago. Like, there was zero progress.”
Zeghidour: Audio watermarking is a scam and easily broken
“Watermarking is a scam. I'm sorry, I have to say it. It just doesn't work. I worked on it. We have an appendix in the Moshi paper around how we could break so easily any watermarking that was supposed to be state of the art. So people should not rely on that.”
Zeghidour: Only 50 people worldwide can train competitive voice AI models
“Between 10 and 100? No, I would say. 50? I don't know. It's hard to say. But, yeah, I think it's very few and, really meaningful contributions that have pushed the field forward have been made by very small groups of people.”
Zeghidour: Voice will be the primary interface for next-gen AI hardware
“In my perception, all the new hardware companies have voice at the heart of the product. All the prototypes that we see, whether it's glasses or pendants or, you know, like the new stuff that Johnny Hive and Sam Altman are working on. Voice is at the heart of …”