Assertion Supported AI assessment confidence: 90% certainty 4/5 debate potential 1/5

Goel: Cartesia runs Sonic TTS model locally on a standard Mac

Karan Goel · No Priors Ep. 70 | With Cartesia Co-Founders Karan Goel & Albert Gu · Jun 27, 2024 · at 31:29

Cartesia co-founder Karan Goel performs a live on-device technical demonstration of Cartesia's Sonic text-to-speech model running on a laptop for hosts Sarah Guo and Elad Gil.

0:00 / 0:32exact quote · 32.9s
▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark
“Yeah, I have a you know, our model running on our standard issue Mac here. Basically, this is you know, our text-to-speech model. Sonic on our playground is running in the cloud, and so you know, part of what I talked about earlier was how do you kind of bring this closer to on-device and edge, and I think the first place to start is your laptop, and then hopefully bring it shrink it down and bring it closer and closer to a smaller footprint. So let me try running this. It's great to be on the No Priors podcast today. You know, we have the same feature set that's in the cloud, but running on this, and.”

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 Karan Goel

Prediction Not checkable as stated
Goel: AI models generating real-time data will replace traditional graphics engines
“In the future, like you will be essentially replacing, you know, graphics and rendering with essentially models that are outputting streams of data. In real time.”
Karan Goel Jun 27, 2024 ▶ 15:10 No Priors Ep. 70 | With Cartesia Co-Founders Karan Goel & Albert Gu
Opinion
Goel: 3B parameter models are still too small and lack strong capabilities
“So the three V models are interesting, I think, but they aren't like, they're still small and not very capable.”
Karan Goel Jun 27, 2024 ▶ 18:23 No Priors Ep. 70 | With Cartesia Co-Founders Karan Goel & Albert Gu
Opinion
Goel: Current AI speech models fail to capture profession-specific vocal nuances
“And that's sort of the nuance that I don't think any models really capture well, which is like, you know, if you're a nurse, you need to talk in a different way than if you're a lawyer, or if you're a judge, or if you're a venture capitalist, you know, very di…”
Karan Goel Jun 27, 2024 ▶ 23:42 No Priors Ep. 70 | With Cartesia Co-Founders Karan Goel & Albert Gu
Disclosure
Goel: Cartesia intends to train an on-device multimodal model
“Yes. But, you know, we have our own sort of set of techniques that we're developing in order to be able to do that effectively. I think that I will maybe leave for another podcast. But I think, yeah, I think that is the intention at the end of the day is build…”
Karan Goel Jun 27, 2024 ▶ 27:54 No Priors Ep. 70 | With Cartesia Co-Founders Karan Goel & Albert Gu
Assertion Supported
Goel: Cartesia's Sonic TTS engine reduces typical voice latency by 150ms
“Even with what we've done with Sonic, we're already kind of shaving off, like, a 150 milliseconds off of you know, what they typically use.”
Karan Goel Jun 27, 2024 ▶ 1:16 No Priors Ep. 70 | With Cartesia Co-Founders Karan Goel & Albert Gu
Disclosure
Goel: Cartesia aims to cut another 600ms of voice latency this year
“And so, you know, the roadmap is let's, let's get to the next 600 milliseconds and try to shape those off in the, over the course of the year.”
Karan Goel Jun 27, 2024 ▶ 1:23 No Priors Ep. 70 | With Cartesia Co-Founders Karan Goel & Albert Gu
Made with StarZero

Turn any episode into a week of clips.

This entire site, over 100 episodes transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.