David Zhao
@davidzh
Followers
2K
Following
8K
Media
33
Statuses
1K
Co-Founder @livekit. Entrepreneur and engineer. I like computers and believe in hard money. #Bitcoin
The Internets
Joined February 2009
Hedra has achieved quite the engineering feat here. They are performing full frame generation - every pixel is synthesized, not just the lips area. Being able to do it at $0.05/min is just 🤯🤯🤯.
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:
0
2
12
RT @imkylecampbell: A lot of people have reached out to me for my @livekit UI integrated with voice agents and avatars, so I made this vide….
0
2
0
If you enjoy building and shipping on Fridays (and on Saturday, Sunday sometimes), we are hiring!
livekit.io
Come build with us.
0
0
4
Them: "Never ship on Fridays". LiveKit on a Friday afternoon:.
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 .
4
2
42
our design team def dials it to 11.
1
0
19
0
7
0
Now you can use Nova Sonic realtime with the most widely used Voice AI framework!. The integration let's you build voice agents using the same high level constructs that Agents framework offers (function calls, multi-agent, etc). Shout-out to the team at AWS Bedrock for building.
#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 . 👉
3
0
9
Inworld's new TTS is rich and expressive! I've been having a lot of fun playing with them. With a competitive cost & low latency TTFB of ~300ms, this is one to watch for in the voice AI space. Give it a try: pip install livekit-agents[inworld].
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 → Why and how we did it
3
1
16
RT @shayneparlo: Ink-Whisper is fast!. @cartesia_ai released a new STT model yesterday, and it's as fast as you'd expect. Streamed transcri….
0
15
0
RT @cartesia_ai: Building voice agents? Meet Ink-Whisper: the fastest, most affordable streaming speech-to-text model. 🌎 Optimized for a….
0
24
0
this is huge! @mem0ai team has made it really straight forward to add memory capabilities to any LiveKit agent.
🚀 We’ve just updated our docs for Mem0 x LiveKit integration with LiveKit Agents 1.0!. Now you can power real-time voice agents with memory - persistent, contextual, and fast. @livekit powers real-time voice - low-latency, rock-solid, and dev-friendly. docs below 👇
3
1
10
RT @daviduche03: i have fully migrated @_brimink to @livekit, it much more faster now, also it's using @tldraw for the canvas, you should t….
0
4
0
RT @tom_shapland: Interruptions are the biggest problem with Voice AI agents. I'm giving a talk on the academic research on turn taking in….
0
3
0