So, you know how voice tech is getting crazy good lately, way beyond
those old robotic voices? If you're curious about how it actually
works, you should join this months Realtime AI Meetup; a panel
conversation discussing Speech-to-Text (STT) and Text-to-Speech (TTS)
models. We're going to pull back the curtain and show you how today's
Text-to-Speech and Speech-to-Text models are really made. We'll delve
into everything, including the challenges of obtaining accurate data
(you know, with all the different accents and emotions) and how models
are actually trained. It's not just about a low error rate; we'll also
discuss how to test for things that are harder to measure, such as
whether a voice sounds natural. The best part is it's all for
developers. You'll get practical advice on the tough stuff, like how
to handle annoying lag in your app and ensure it works even in a noisy
environment. Seriously, if you're looking to build a voice-powered
app, you should join us on Tuesday, June 17th, from 5:30 PM - 8:00 PM
PDT. Following the panel discussion we'll be hosting our Developer
Showcase where you'll learn about whats new and cool in the world of
realtime AI. As always, we'll have plenty of time for introductions,
food, drinks, and connecting with the Realtime AI community. See you
there! Panelists: • Eli Landau (Speechmatics) • Jean Wang (Inworld
AI) Moderator: Michael Solati (LiveKit) Schedule: 5:30 – 6:00 PM:
Introductions, drinks, and networking 6:00 – 6:05 PM: Developer
Showcase: PrepPal 6:05 – 6:10 PM: Developer Showcase: Pipelogic 6:10
– 6:15 PM: Developer Showcase: Chatterbox 6:15 – 6:55 PM: Panel
Discussion 6:55 – 7:05 PM: Developer Showcase: Speechmatics 7:05 –
7:15 PM: Developer Showcase: Inworld AI 7:15 – 8:00 PM: Food,
drinks, and networking
food
159
Views
10/07/2025 Last update