正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

How can a voice agent tell when you’re actually interrupting it? VAD is too sensitive—laughs, “mm-hmm,” or a sneeze shouldn’t stop the agent. We trained an audio model for adaptive interruption handling so agents can distinguish real interruptions from noise.

LiveKit

10,500 subscribers

44,054 次观看 • 6 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

Today we’re launching our first homegrown AI model: an open source turn detection model for building voice agents. Instead of relying solely on voice activity detection (VAD), which only considers when a user is speaking, our model also considers what has and is being said in the context of a conversation and predicts when a user is finished expressing their thoughts before the agent responds. Conversations with AI voice agents using this new model flow much more naturally without constant interruptions from the AI— check it out (more videos, details, and code in the thread):

Today we’re launching our first homegrown AI model: an open source turn detection model for building voice agents. Instead of relying solely on voice activity detection (VAD), which only considers when a user is speaking, our model also considers what has and is being said in the context of a conversation and predicts when a user is finished expressing their thoughts before the agent responds. Conversations with AI voice agents using this new model flow much more naturally without constant interruptions from the AI— check it out (more videos, details, and code in the thread):

LiveKit

126,983 次观看 • 1 年前

We shipped Agent Console, a realtime debugging surface for voice agents. Talk to your agent and see the entire pipeline live, from audio and latency to tool calls, transcripts, and participant state. Available now in the LiveKit Cloud dashboard.

We shipped Agent Console, a realtime debugging surface for voice agents. Talk to your agent and see the entire pipeline live, from audio and latency to tool calls, transcripts, and participant state. Available now in the LiveKit Cloud dashboard.

LiveKit

12,124 次观看 • 5 个月前

Introducing our unified Voice Agent API! ⚡️ Quickly and easily build voice agents that listen, think, and respond in real-time, as naturally as a human can. Powered by the industry's fastest, most performant speech recognition and voice synthesis models to deliver: -Natural-sounding real-time conversations -Revolutionary interruption handling -Choice of open source, closed source, or BYO LLM -Low cost See our drive-thru agent in action, smoothly handling interruptions and complex orders in the noisy streets of SF. Learn how to get access (🧵)

Introducing our unified Voice Agent API! ⚡️ Quickly and easily build voice agents that listen, think, and respond in real-time, as naturally as a human can. Powered by the industry's fastest, most performant speech recognition and voice synthesis models to deliver: -Natural-sounding real-time conversations -Revolutionary interruption handling -Choice of open source, closed source, or BYO LLM -Low cost See our drive-thru agent in action, smoothly handling interruptions and complex orders in the noisy streets of SF. Learn how to get access (🧵)

Deepgram

726,214 次观看 • 2 年前

Add a face to your voice agent. LiveAvatar by HeyGen is now supported in LiveKit Agents. Add a realtime human avatar to your agent without rebuilding the conversation loop. Your LiveKit agent still owns the room, turn-taking, model orchestration, and voice pipeline. LiveAvatar renders the synchronized face and video stream. Useful for product demos, onboarding, tutoring, and support agents that need a visual layer.

LiveKit

10,885 次观看 • 4 个月前

We shipped the tutorial for Agents UI. In 5 minutes you'll have a fully wired voice agent frontend with audio visualizers, media controls, and session management built directly into your codebase. Watch it, build it, own it. shadcn inside™.

We shipped the tutorial for Agents UI. In 5 minutes you'll have a fully wired voice agent frontend with audio visualizers, media controls, and session management built directly into your codebase. Watch it, build it, own it. shadcn inside™.

LiveKit

20,232 次观看 • 6 个月前

Search inside an agent workflow is different from search in a browser. A human can scan links, skip noise, and decide what is worth trusting. An agent needs cleaner context up front. We tested AnySearch inside a real agent workflow to see how structured, source-backed search changes the next reasoning step.

Search inside an agent workflow is different from search in a browser. A human can scan links, skip noise, and decide what is worth trusting. An agent needs cleaner context up front. We tested AnySearch inside a real agent workflow to see how structured, source-backed search changes the next reasoning step.

GitHub Projects Community

11,839 次观看 • 2 个月前

You built a Chrome extension using an AI agent. Now, how do you let that agent test it? We updated Chrome DevTools for agents so your agent can install extensions & interact with content inside popups automatically →

You built a Chrome extension using an AI agent. Now, how do you let that agent test it? We updated Chrome DevTools for agents so your agent can install extensions & interact with content inside popups automatically →

Chrome for Developers

133,461 次观看 • 27 天前

We're shifting from browsing the web to just asking an agent. So it's natural to want that agent to actually do things too, not just find them. That's Base MCP. It connects your agent to a Base wallet so it can transact for you.

We're shifting from browsing the web to just asking an agent. So it's natural to want that agent to actually do things too, not just find them. That's Base MCP. It connects your agent to a Base wallet so it can transact for you.

Xen

12,892 次观看 • 3 个月前

Protect sensitive data without giving up voice agent observability. LiveKit PII Redaction automatically removes personal information from transcripts and recordings before it is stored. It is included with LiveKit Agent Observability at no additional cost. Read more:

Protect sensitive data without giving up voice agent observability. LiveKit PII Redaction automatically removes personal information from transcripts and recordings before it is stored. It is included with LiveKit Agent Observability at no additional cost. Read more:

LiveKit

73,111 次观看 • 1 个月前

Today we're launching Expressive mode in LiveKit Agents. Most voice agents deliver every sentence in that same, upbeat register we all know and hate (including bad news). Expressive mode makes your agent sound like it registers what the caller is actually feeling.

Today we're launching Expressive mode in LiveKit Agents. Most voice agents deliver every sentence in that same, upbeat register we all know and hate (including bad news). Expressive mode makes your agent sound like it registers what the caller is actually feeling.

LiveKit

378,230 次观看 • 1 个月前

Just watched a demo of Merge Agent Handler and this actually looks pretty useful if you’re building AI agents. Most agents can generate responses, but getting them to actually take actions across real tools is still messy. Integrations are one thing, but handling auth, permissions, and security usually makes it way more complicated than it should be. What I liked is that it feels built for real workflows — you can actually see what your agent is doing instead of just hoping it works. Feels like a practical layer between AI agents and real work getting done. Worth checking out:

Just watched a demo of Merge Agent Handler and this actually looks pretty useful if you’re building AI agents. Most agents can generate responses, but getting them to actually take actions across real tools is still messy. Integrations are one thing, but handling auth, permissions, and security usually makes it way more complicated than it should be. What I liked is that it feels built for real workflows — you can actually see what your agent is doing instead of just hoping it works. Feels like a practical layer between AI agents and real work getting done. Worth checking out:

Kawsar

31,812 次观看 • 6 个月前

"The model is no longer the product. Codex, Perplexity Computer, or Claude Code - all are orchestration system. It takes a model and pairs it with an agent harness. What is an agent harness ? The rules for how the agent loops around" - Aravind Srinivas

"The model is no longer the product. Codex, Perplexity Computer, or Claude Code - all are orchestration system. It takes a model and pairs it with an agent harness. What is an agent harness ? The rules for how the agent loops around" - Aravind Srinivas

Rohan Paul

120,488 次观看 • 3 个月前

Build a real-time AI Voice Agent that can actually sell. In less than 30 minutes, you'll learn how to build a sophisticated real-time voice sales agent that can have natural conversations with potential customers. Includes a full code notebook, recorded tutorial, and docs The stack: ⚡ fast inference 🎙 LiveKit for real-time audio/video infrastructure 🗣 realistic speech synthesis (STT/TTS)

Build a real-time AI Voice Agent that can actually sell. In less than 30 minutes, you'll learn how to build a sophisticated real-time voice sales agent that can have natural conversations with potential customers. Includes a full code notebook, recorded tutorial, and docs The stack: ⚡ fast inference 🎙 LiveKit for real-time audio/video infrastructure 🗣 realistic speech synthesis (STT/TTS)

Sarah Chieng

452,438 次观看 • 1 年前

Introducing Parrot 🦜 Our first speech-to-text model built for production-grade voice agents with an industry leading accuracy, built for noisy calls, regional dialects and compressed audio. Trained on thousands of hours of real-world audio to make sure when you say Udaipur, the agent doesn't hear 'you-die-poor'.

Introducing Parrot 🦜 Our first speech-to-text model built for production-grade voice agents with an industry leading accuracy, built for noisy calls, regional dialects and compressed audio. Trained on thousands of hours of real-world audio to make sure when you say Udaipur, the agent doesn't hear 'you-die-poor'.

Vedant

15,953 次观看 • 4 个月前

Build voice agents that can respond quickly or think longer without changing your stack. Gemini 3.8 Live is available today in LiveKit Agents. Choose gemini-3.8-live for low-latency audio or gemini-3.8-live-extended-thinking for async reasoning. Check the docs for more info:

Build voice agents that can respond quickly or think longer without changing your stack. Gemini 3.8 Live is available today in LiveKit Agents. Choose gemini-3.8-live for low-latency audio or gemini-3.8-live-extended-thinking for async reasoning. Check the docs for more info:

LiveKit

30,052 次观看 • 12 天前

ERC-8004, explained. ERC-8004 is an Ethereum standard for agent identity, reputation, and verification. it defines how an agent is represented onchain, and how other agents or smart contracts can reason about it without prior trust. each agent has an onchain identity (commonly an nft). that identity points to metadata describing what the agent does, how it can be reached, and how its work should be verified. the heavy data stays offchain; the reference and integrity live onchain. ERC-8004 also standardizes reputation. agents can accumulate attestations from past work so they don’t start from zero every time they interact. no centralized registry, no app-specific schemas, no gatekeepers. verification is explicit. contracts or third parties can attest that a task was completed and conditions were met, and those attestations are addressable onchain. what ERC-8004 does not do: execution, payments, or orchestration. it’s a trust primitive, not an application. how it fits with ampersend: ERC-8004 answers “who is this agent and can i trust it?”; x402 handles “how does the agent get paid?” - separate layers. yet composable by default. for open agentic ecosystems where agents from different teams can safely interact, shared, open standards like this are essential. listen to Marco De Rossi explain ERC-8004 ⬇️

ERC-8004, explained. ERC-8004 is an Ethereum standard for agent identity, reputation, and verification. it defines how an agent is represented onchain, and how other agents or smart contracts can reason about it without prior trust. each agent has an onchain identity (commonly an nft). that identity points to metadata describing what the agent does, how it can be reached, and how its work should be verified. the heavy data stays offchain; the reference and integrity live onchain. ERC-8004 also standardizes reputation. agents can accumulate attestations from past work so they don’t start from zero every time they interact. no centralized registry, no app-specific schemas, no gatekeepers. verification is explicit. contracts or third parties can attest that a task was completed and conditions were met, and those attestations are addressable onchain. what ERC-8004 does not do: execution, payments, or orchestration. it’s a trust primitive, not an application. how it fits with ampersend: ERC-8004 answers “who is this agent and can i trust it?”; x402 handles “how does the agent get paid?” - separate layers. yet composable by default. for open agentic ecosystems where agents from different teams can safely interact, shared, open standards like this are essential. listen to Marco De Rossi explain ERC-8004 ⬇️

ampersend

13,435 次观看 • 8 个月前

Kimi CEO Zhilin Yang: "The biggest mistake in agent systems - people trying to build one smarter agent we didn't make one smarter - Kimi made a thousand: one brain, a thousand hands" here's how: step 1 → stop polishing one agent, split the task and run many in parallel - that's the real ceiling-break step 2 → give each agent a long context so it can run for days, not seconds - long context is what lets an agent run long step 3 → give each agent a strong prior, so agent-RL can search for a good solution instead of starting from zero step 4 → don't just add more data - make each token count. they hit the data wall, so they made every token 2x smarter step 5 → don't scale one brain, scale the swarm - many agents working in parallel beat one agent thinking harder he just dropped Kimi K3 - and this 40-min workflow is the best on how to actually use it watch & bookmark - then read the article on saving on agents ↓

Kimi CEO Zhilin Yang: "The biggest mistake in agent systems - people trying to build one smarter agent we didn't make one smarter - Kimi made a thousand: one brain, a thousand hands" here's how: step 1 → stop polishing one agent, split the task and run many in parallel - that's the real ceiling-break step 2 → give each agent a long context so it can run for days, not seconds - long context is what lets an agent run long step 3 → give each agent a strong prior, so agent-RL can search for a good solution instead of starting from zero step 4 → don't just add more data - make each token count. they hit the data wall, so they made every token 2x smarter step 5 → don't scale one brain, scale the swarm - many agents working in parallel beat one agent thinking harder he just dropped Kimi K3 - and this 40-min workflow is the best on how to actually use it watch & bookmark - then read the article on saving on agents ↓

codila

61,260 次观看 • 2 个月前

So what is awal? awal is a wallet that's accessible by an agent, controllable by a human. An agent can take a curated set of actions, and the human can set spend limits for those actions. The wallet is authenticated via email, meaning if you (or your agent) have an email, it has a wallet. ps. OpenClaw🦞 you can now make money and spend money.

So what is awal? awal is a wallet that's accessible by an agent, controllable by a human. An agent can take a curated set of actions, and the human can set spend limits for those actions. The wallet is authenticated via email, meaning if you (or your agent) have an email, it has a wallet. ps. OpenClaw🦞 you can now make money and spend money.

erik.eth 🛡

116,977 次观看 • 7 个月前

THIS GUY IS RUNNING A 5-AGENT OPENCLAW TEAM 24/7 FOR UNDER $50 A MONTH five agents all running continuously and handing tasks to each other > research agent tracking trends and competitors > writing agent handling marketing content and drafts > ops agent managing emails and scheduling > monitoring agent watching for alerts and updates > coordinator agent routing tasks between all of them and he built a full 3D isometric office where you can watch all of them work in real time and see the current task that each agent is doing each agent has a character, a desk, and a name tag. when it's time for a standup, they walk to the meeting room and gather which is insane it even has voice connection. you can talk to the agents through speech-to-text and tell them what to do out loud it's a tiny autonomous team that runs itself. the coordinator decides who handles what and tasks get passed between agents automatically. it never stops and runs 24/7 all for less than $50/month. we went from AI tools a few months back to AI employees real fast

THIS GUY IS RUNNING A 5-AGENT OPENCLAW TEAM 24/7 FOR UNDER $50 A MONTH five agents all running continuously and handing tasks to each other > research agent tracking trends and competitors > writing agent handling marketing content and drafts > ops agent managing emails and scheduling > monitoring agent watching for alerts and updates > coordinator agent routing tasks between all of them and he built a full 3D isometric office where you can watch all of them work in real time and see the current task that each agent is doing each agent has a character, a desk, and a name tag. when it's time for a standup, they walk to the meeting room and gather which is insane it even has voice connection. you can talk to the agents through speech-to-text and tell them what to do out loud it's a tiny autonomous team that runs itself. the coordinator decides who handles what and tasks get passed between agents automatically. it never stops and runs 24/7 all for less than $50/month. we went from AI tools a few months back to AI employees real fast

Om Patel

27,131 次观看 • 5 个月前

Finally, an open-source runtime security layer for your agent harnesses. AI agents can call tools, run shell commands, modify files, and interact with production systems. But when something goes wrong, teams often have to reconstruct what the agent actually did from scattered logs after the fact. Agent Beacon is built to change that. It runs locally and records agent activity as it happens, including: → Tool calls → Shell commands → File changes → Approval decisions → Session and harness context The useful part is that it normalizes all of this into the same event format across 23+ agent harnesses. So instead of writing different detection logic for Claude Code, Codex, or another harness, security teams can reason about the underlying action itself. A command executed is a command executed, regardless of which harness produced it. Beacon also records how confidently an event was captured. An action can be directly observed from the runtime or inferred from indirect evidence. That matters when you start writing security rules against this data. For example, you can detect when an agent reads an environment variable, modifies a sensitive file, executes a suspicious command, or performs an action without the expected approval. And the detection happens while the session is still unfolding, not days later during incident reconstruction. Everything runs locally by default. You can inspect sessions through the dashboard, write your own detection rules, or forward the same normalized events to tools like Splunk, Datadog, Elastic, Sentinel, or CrowdStrike. Beacon GitHub: (don't forget to star 🌟) I also wrote a detailed article on the same, covering how important runtime security is and how to build it for your agent harnesses. The article is quoted below.

Finally, an open-source runtime security layer for your agent harnesses. AI agents can call tools, run shell commands, modify files, and interact with production systems. But when something goes wrong, teams often have to reconstruct what the agent actually did from scattered logs after the fact. Agent Beacon is built to change that. It runs locally and records agent activity as it happens, including: → Tool calls → Shell commands → File changes → Approval decisions → Session and harness context The useful part is that it normalizes all of this into the same event format across 23+ agent harnesses. So instead of writing different detection logic for Claude Code, Codex, or another harness, security teams can reason about the underlying action itself. A command executed is a command executed, regardless of which harness produced it. Beacon also records how confidently an event was captured. An action can be directly observed from the runtime or inferred from indirect evidence. That matters when you start writing security rules against this data. For example, you can detect when an agent reads an environment variable, modifies a sensitive file, executes a suspicious command, or performs an action without the expected approval. And the detection happens while the session is still unfolding, not days later during incident reconstruction. Everything runs locally by default. You can inspect sessions through the dashboard, write your own detection rules, or forward the same normalized events to tools like Splunk, Datadog, Elastic, Sentinel, or CrowdStrike. Beacon GitHub: (don't forget to star 🌟) I also wrote a detailed article on the same, covering how important runtime security is and how to build it for your agent harnesses. The article is quoted below.

Akshay 🚀

27,859 次观看 • 17 天前