Cheeky Pint cover image

The world of voice AI, with Mati Staniszewski of ElevenLabs

Cheeky Pint

00:00

Cascaded systems beat speech-to-speech today

Mati Staniszewski says text-mediated pipelines remain more reliable and controllable than direct speech-to-speech models, despite latency advantages of fused approaches.

Play episode from 27:42
Transcript

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app