Dad to Izzy, husband to @maggdominguez. Head of Product at @LiveKit (he/him/his)
San Francisco, CA
Joined September 2007
- Tweets3.6K
- Following510
- Followers6.2K
- Likes5.5K
Ben Cherry retweeted
I just want to echo this best invention of 2026 for the @aura_frames eink
It shows one picture a day. And sits on a ledge on the stairs since it doesn’t require a plug. Each day’s picture becomes a conversation in our home about the memory.
time.com/collection/best-inv…
Ben Cherry retweeted
It's misleading to run a benchmark focused on noise, and then specifically turn off noise cancellation in stacks where you have control. (pretty sure Grok does not give you that level control)
livekit does a great job with noise/background voice when you allow it to. (and glad to see we are beating every other cascaded pipelines)
Ben Cherry retweeted
We just raised $4M at @lightsagehq , led by @nexusvp , to build the growth stack for internet’s newest customer: AI agents.
Claude Code, Codex, Cursor and other agents can already discover products, compare alternatives, read documentation, install SDKs, call APIs and start using software on behalf of humans. Soon, they’ll increasingly transact too and that changes how internet companies grow.
For decades, companies built growth infrastructure around humans. PLG helped humans adopt products. Now there’s a new journey to optimize: Can an AI agent discover you, choose you, successfully use you, and eventually pay for you?
We call this Agent-Led Growth.
Lightsage helps companies get discovered, recommended and used by agents
→ Agent Discovery - when and why agents recommend you vs. competitors
→ Agent Experience - whether agents can successfully use your APIs, SDKs, CLIs, MCP servers and agent skills
→ Agent Analytics - what real agents do when they reach your website, docs and product. and most recently agent-attributed traffic conversion.
Companies including @firecrawl , @reductoai , @daytonaio , @rimelabs , @Tiny_Fish and @insforge are already using Lightsage to build their agent-led growth strategy and improve their agent journey.
We’re incredibly grateful to have Nexus lead this round alongside these amazing founders and operators.
- Former Salesforce CTO Steven Tamm
- Postman CEO @a85
- Apollo CEO Matt Curl
- DocuSign President Robert Chatwani
- Former GitLab Head of Growth @HilaQu
- Resend CEO @zenorocha
- Firecrawl Co-founder @ericciarla
- Daytona CEO @ivanburazin
- Tinyfish COO @shuhao_friday
- Adam Frankl
and many more!
As agents increasingly discover, evaluate, use and pay for products on our behalf, we believe every company will need to understand and optimize for the agent channel.
That’s what we’re building Lightsage for.
Huge thank you to my co-founder Sean Er, customers, early investors @AlchemistAcc and everyone who believed in us early. Honoured to be featured in @Forbes .
We’re just getting started.
lightsage.com
Ben Cherry retweeted
We built a patient intake agent with @spacexai that runs end to end on Grok voice models.
Grok STT → Grok 4.3 → Grok TTS, cascaded through LiveKit Inference. Three model strings in one AgentSession. No separate API key, no separate billing, ZDR on every hop.
Talk to it: xai.livekit.space
Ben Cherry retweeted
Frontier models keep getting smarter…and slower. This is bad for voice agents, where every millisecond before the first word counts.
So we optimized for speed. Introducing Gemma 4 31B on LiveKit Inference:
🗣️ 381ms to first sentence — 2x+ faster than the next model
✅ 88% task completion (see the criteria in reply)
💰 $1.20 / 1M output tokens
Fast enough for real conversation, smart enough for effective agents.
Ben Cherry retweeted
Since livekit-wakeword release, the number one question we’ve been asked is if we support wake word in other languages.
The answer is yes. By leveraging VoxCPM2 from @OpenBMB, we can generate samples in 30 languages and train on them.
All local. All in a single command. All open-source.
Ben Cherry retweeted
Introducing Agents UI, an open-source @shadcn component library for building polished React frontends for your voice agents.
Audio visualizers. Media controls. Session management tools. Chat transcripts. All wired to LiveKit Agents.
Install via the shadcn CLI and own the code.
Ben Cherry retweeted
This decision makes America less safe, today and tomorrow. Pete Hegseth just told the entire U.S. tech sector: don't make a deal with the U.S. military because my next meltdown might mark you as more dangerous than China.
It turns out, nothing is undermining our military capabilities more than Pete Hegseth and Donald Trump's fragile masculinity.
This week, Anthropic delivered a master class in arrogance and betrayal as well as a textbook case of how not to do business with the United States Government or the Pentagon.
Our position has never wavered and will never waver: the Department of War must have full, unrestricted access to Anthropic’s models for every LAWFUL purpose in defense of the Republic.
Instead, @AnthropicAI and its CEO @DarioAmodei, have chosen duplicity. Cloaked in the sanctimonious rhetoric of “effective altruism,” they have attempted to strong-arm the United States military into submission - a cowardly act of corporate virtue-signaling that places Silicon Valley ideology above American lives.
The Terms of Service of Anthropic’s defective altruism will never outweigh the safety, the readiness, or the lives of American troops on the battlefield.
Their true objective is unmistakable: to seize veto power over the operational decisions of the United States military. That is unacceptable.
As President Trump stated on Truth Social, the Commander-in-Chief and the American people alone will determine the destiny of our armed forces, not unelected tech executives.
Anthropic’s stance is fundamentally incompatible with American principles. Their relationship with the United States Armed Forces and the Federal Government has therefore been permanently altered.
In conjunction with the President's directive for the Federal Government to cease all use of Anthropic's technology, I am directing the Department of War to designate Anthropic a Supply-Chain Risk to National Security. Effective immediately, no contractor, supplier, or partner that does business with the United States military may conduct any commercial activity with Anthropic. Anthropic will continue to provide the Department of War its services for a period of no more than six months to allow for a seamless transition to a better and more patriotic service.
America’s warfighters will never be held hostage by the ideological whims of Big Tech. This decision is final.
Ben Cherry retweeted
Hey @ycombinator & @amiklas… we heard you’re looking for us 👀
We’d be happy to show you what we’ve built so far, and we may even have a little room left in the round. 😉
DM and check out trydotted.com
Ben Cherry retweeted
This is absolutely shameful. Agents of a federal agency unnecessarily escalating, and then executing a defenseless citizen whose offense appears to be using his cell phone camera. Every person regardless of political affiliation should be denouncing this.
Ben Cherry retweeted
Love love love @livekit's example repos. Every developer should have a docs MCP and instructions on how to set it up. And look at those AGENTS and CLAUDE md files
Ben Cherry retweeted
Join us on 10/1 at 5:30p for the first Physical AI Meetup hosted by @livekit at @frontiertower.
Come for robot demos, panel discussion with industry leaders, food, drinks & networking.
luma.com/physical-ai-meetup
Ben Cherry retweeted
Serverless voice agents are here.
Two years ago, we worked with OpenAI to plan the ChatGPT Voice Mode launch.
Voice agents were different from web apps:
• sessions last minutes to hours
• what’s said next depends on what was said before
• UX breaks even with moderate latency
• CPU/memory usage isn’t uniform
Scaling voice agents is more like scaling a multiplayer video game. To do it right, you need tech for load balancing, capacity management, deploying updates, and observability.
We’ve seen voice AI devs spend time building this in-house over and over — a clear sign that deployment and scaling are undifferentiated problems.
So starting today, you can push your agent code directly to LiveKit Cloud and we’ll handle the hard parts for you. Try it out — and DM me your feedback.
Ben Cherry retweeted
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 ...
Ben Cherry retweeted
Interruptions are the biggest problem with Voice AI agents. I'm giving a talk on the academic research on turn taking in human conversation, and the SOTA end of turn models used in Voice AI, at the @aiDotEngineer World's Fair tomorrow. Hope to see you there!
Ben Cherry retweeted
I built a voice shopping assistant that can be used on every Shopify store in a DAY—that's how good new storefront MCP support from @ShopifyDevs is 🤯
Wired up w/ @livekit + @cartesia. Turn detection, interruption handling, all audio over WebRTC. Code and architecture in 🧵
Ben Cherry retweeted
I'm super pumped about this one—we partnered with @tavus on a plugin to simplify the process of building realtime AI avatars.
There's a crazy amount of complexity to realtime procedural video generation that we just handle.
In two lines of code—add an avatar to any agent.
Ben Cherry retweeted
Learn to build conversational AI voice agents in "Building AI Voice Agents for Production", created in collaboration with @livekit and @realavatarai, and taught by @dsa (Co-founder & CEO of LiveKit), @shayneparlo (Developer Advocate, LiveKit), and @nedteneva (Head of AI at RealAvatar, an AI Fund portfolio company).
Voice agents combine speech and reasoning capabilities to enable real-time conversations. They're already being used to support customer service, to improve accessibility in healthcare, for entertainment applications, and for talk therapy.
In this course, you’ll learn to build voice agents that listen, reason, and respond naturally. You’ll follow the architecture used to create the "AI Andrew" Avatar, a collaborative project between DeepLearning.AI and RealAvatar that responds to users in what sounds like my voice. You’ll build a voice agent from scratch and deploy it to the cloud, enabling support for many simultaneous users.
What you’ll learn:
- Understand the fundamentals of voice agents, including key components like speech-to-text (STT), text-to-speech (TTS), and LLMs, and how latency is introduced at each layer.
- Explore voice agent architectures and the trade-offs between modular pipelines and speech-to-speech APIs.
- Explore how platforms like LiveKit mitigate latency issues with optimized networking infrastructure and low-latency communication protocols.
- Learn how to connect client devices to voice agents using WebRTC—and why it outperforms HTTP and WebSocket for low-latency audio streaming.
- Incorporate voice activity detection (VAD), end-of-turn detection, and context management to detect turns, handle interruptions, and manage conversational flow.
- Understand the trade-offs between latency, quality, and cost in an example in which you build a voice agent and change its voice.
- Equip your agent with metrics to measure latency at each stage of the voice pipeline and learn the key levers you can pull to make your agent faster and more responsive.
The voice agents built in this course also incorporate voice technology from @elevenlabs, a supporting contributor to the project.
By the end of this course, you'll have learned the components of an AI voice agent pipeline, combined them into a system with low-latency communication, and deployed them on cloud infrastructure so it scales to many users.
I’m looking forward to seeing what voice agents you build from this course!
Please sign up here: deeplearning.ai/short-course…
Ben Cherry retweeted
Devs building in voice and video AI, we’ve got something special cooked up for next week — on 4/30, we’re doing a fireside chat with @juberti in SF.
Justin is a legend. He created the WebRTC protocol, led dev for Google Meet and Stadia, started @FixieAI, and is now the Head of Realtime AI at @OpenAI.
Come hang out with us @fdotinc, there will be lots of food and good vibes!
ALT Promotional graphic for a 'Realtime AI Meetup' taking place on April 30 at Founders Inc in Fort Mason, San Francisco. The design features a black background with small white pixel-like dots, giving a starry effect. Partner logos for OpenAI, LiveKit, Founders, Inc., and Sierra appear at the bottom.