dsa
@dsa
early yc, early twitter, early 23andme, late bloomer @livekit
Announcing LiveKit Agents 1.0 and a $45M Series B Back when we launched ChatGPT Voice Mode with OpenAI, voice AI was not a thing. Now it's a whole ecosystem of companies, products, and tools. LiveKit’s infra for building and running voice AI agents is also at scale: over 100K…
The @livekit Agents 1.2 release is packed with stuff, but most importantly it lays the groundwork for being able to programmatically test and evaluate voice agents directly within the framework. Let’s get more voice agent demos into prod! 🚀
Agents 1.2 for Python is now released! This includes our new test framework, observability w/ OpenTelemetry traces, half-duplex support (swapping a realtime model's voice w/ your own TTS), significant improvements to end of turn model (now with Hindi) and more! Let's dig in ...
We’ve added WebRTC support to ElevenLabs Conversational AI, enabling best-in-class echo cancellation and background noise removal for your AI agents.
The @hedra_labs Realtime Avatar API is here! Let's look at exactly how it works using 4 different use cases: 1. Pipeline using STT -> LLM -> TTS 2. Using the OpenAI Realtime API 3. Avatars created dynamically by an LLM 4. Education focused avatar w/ advanced frontend features
We’ve entered the era of AI agents. Voice may be the interface, but video is the next unlock. Today, we’re launching Hedra Live Avatars, the most advanced streaming avatar model in the world. - Low cost: Just $0.05/min — 15x cheaper than existing solutions - Ultra-low latency:…
Steph Curry gets paid $50m to throw a ball into a hoop, so why is it outlandish for Zuck to pay someone $250m to build AGI?
This example / demo with @inworld_ai is probably the most fun I've ever had building one. Tabletop-like w/ skill checks, combat, gearing, barter system, XP, all AI generated in realtime. Kept wanting to add more—scope def creeped a lot. Code + key decisions below ...
Did you know you can access @inworld_ai TTS via @livekit's agents framework plugin? Now, you can create previously unimaginable, real-time voice experiences such as multiplayer games, agentic NPCs, customer-facing avatars, live training simulations, and more. It’s studio…
#AmazonNova Sonic now integrates with @livekit’s WebRTC infrastructure 🚀🎉⚡ This integration streamlines the development of voice-first AI application by removing the complexity of managing real-time audio infrastructure. #AWS #generativeAI 👉 go.aws/4lhtJ4P
Queueing at 11:30a on Friday for play on Saturday, and not even in the first 500 for Centre Court!
Great opportunity. Evan and @quintendf are among the most thoughtful product designers out there. The Tolan onboarding flow is 🤌
building a great companion is great fun. and it's working. Tolan sits at the frontier of embodiment, memory, and voice AI. if you're a staff level ios, unity, or platform engineer and find that interesting, reach out → [email protected]
🚀 Deploying a real-time AI voice agent with ~500ms latency — globally. We just dropped a full breakdown of how to assemble a low-latency speech pipeline using STT, LLMs, and TTS, optimized for production use. Here’s how we did it with @livekit 🧵
We just made state-of-the-art TTS 20x more affordable. $5 per million characters. And we're open sourcing the training and modeling code (built on Llama). Because scaling voice AI shouldn't break your budget. Technical Details → Inworld.ai/blog/introduci… Why and how we did it…
Let's build a real-time Voice RAG Agent, step-by-step:
Me: So my friend just launched this co Mom: What’s it do? Me: It aggregates together the output from multiple LLMs and… Mom: Oh, you mean Yupp? $33m seed! @pankaj