| |
|
| |
Join AssemblyAI & LiveKit for an evening with teams building voice agents on our stack-including Boardy, our co-host for the night.
We'll kick things off with a live demo of Universal-3.5 Pro Realtime, AssemblyAI's newest Realtime speech-to-text model, now available on LiveKit Inference.
We'll show how Context Carryover, conversation memory, multilingual support, & Voice Focus help voice agents built on LiveKit better understand users in real-world conversations.
Then you'll hear from builders at Boardy & Flagler Health on what it actually takes to ship a voice agent that works in production.
Before the event, you can choose to get a call from Boardy- a fully conversational AI matchmaker- to hear about who you are, why you're coming, & who you want to meet, then line up introductions with the right people. AI you get to talk to, not just hear about.
Panelists
Owen Gretzinger - Head of Engineering at Boardy
Dylan Wight - Sr. Engineer at Flagler Health
Moderated by Ryan Seams - VP of Customer Solutions at AssemblyAI
Agenda
5:00-6:00 pm - Networking + Happy Hour
6:00-6:15 pm - Live Demo 3.5 Pro Realtime
6:15-7:00 pm - Panel + Q&A
7:00-8:00 pm - Networking
assemblyai.com | Check out 3.5 Pro Realtime
What's New with Universal-3.5 Pro Realtime
Context carryover - agent_context feeds in the agent's question so the model hears the answer through it; 10.2% lower WER across a 20,000-file benchmark.
Conversation memory, on by default - a rolling memory of the call with nothing to configure.
Code-switching across 18 languages - mid-sentence switching, Hinglish included, plus language_code steering when you already know which one.
Voice Focus & speaker labels - voice_focus isolates the primary speaker; labels re-cluster at stream end for up to 10 speakers.
Limited Capacity
Seats are limited. Request an invite to join the community building the future of voice AI!
By signing up for this event, you opt in to receiving AssemblyAI marketing emails. You may unsubscribe at any time. By attending this event, you acknowledge that photography & video recording may take place; if you do not consent, please contact the event host.
|
|
|
|
|
|
|
|
