正在加载视频...

视频加载失败

A quick live sample from ElevenLabs Summit: a future where agents are proactive, not reactive, and can understand the emotional nuance. Here, an agent calls a citizen (me!) with a new programme to help scale their business. All powered by v3 + Expressive Mode in ElevenAgents.

43,891 次观看 • 7 个月前 •via X (Twitter)

33 条评论

Matthew Tyrer 的头像
Matthew Tyrer7 个月前

@matiii I look forward to my phone being flooded with AI scam calls in a years time, thanks.

Christine 的头像
Christine7 个月前

@matiii @elevenlabs I don’t know who you are but I hate this and I also hate you x

Uri Aguilera 的头像
Uri Aguilera7 个月前

@matiii Would’ve loved a ton more of agent stress-testing Mati, that conversation wasn’t very meaningul..!

Mati Staniszewski 的头像
Mati Staniszewski7 个月前

Full demo coming soon - lots of interactions before (and explicit opt in for agent to call me back)

Kacper 的头像
Kacper7 个月前

@matiii @elevenlabs Nothing annoys me more than AI bots calling and making me annoyed.

WorkyJ 的头像
WorkyJ7 个月前

@matiii @elevenlabs Your new business doing what? Scaling by selling to who? We’re all on ubi dude, I ain’t buying your shit, I’m buying the heroin again.

Jesse Jameson 的头像
Jesse Jameson7 个月前

@matiii Not much mention of the biometric data you extracted from voice actors.

Sardor 的头像
Sardor7 个月前

@matiii From an infra perspective, what’s your current end-to-end latency over SIP? We’re benchmarking similar pipelines and would love to compare notes.

Matt Hawrot 的头像
Matt Hawrot7 个月前

@matiii @elevenlabs great job

Ronan.m.Donnelly 的头像
Ronan.m.Donnelly7 个月前

@matiii Still sounds shite mate

Alone Musk 的头像
Alone Musk7 个月前

@matiii @elevenlabs ElevenAgents is the future AI customer experience / sales agent. It’s all about training now. Everyone start making detailed docs. Think about insane savings in costs

Shaq 的头像
Shaq7 个月前

@matiii You guys smashed it - it was such an impressive demonstration of product excellence & engrossing storytelling 👏

Les Yetton 的头像
Les Yetton7 个月前

@matiii Great.. But sounds so fake still.

✝️ We Need an Ark 的头像
✝️ We Need an Ark7 个月前

@matiii @elevenlabs This could have been compelling if it sounded like the conversation was interactive. This technology will only be any use if it can handle being interrupted and disrupted better than an average human.

Alan Swan 的头像
Alan Swan7 个月前

@matiii @elevenlabs Can’t wait to hear an agent demo getting roared at for a cancelled flight 😭 I think real world customer service calls will be the tipping point for adoption

Leo Nonato 的头像
Leo Nonato7 个月前

@matiii @elevenlabs ☝️🏆

Adarsh Kant 的头像
Adarsh Kant7 个月前

@matiii The shift from reactive to proactive is the real unlock. Most voice agents just wait for input. But the best CX happens when AI anticipates needs - like a concierge who reaches out before you ask. Expressive Mode + proactive outreach = agents people want to talk to.

Alan 的头像
Alan7 个月前

@matiii kinda wild to think about proactive agents, right? feels like we’re finally catching up with sci-fi or something. but will they really get the emotional stuff? or just read scripts? either way, i guess it’s nice to dream about scaling without drowning in the chaos

directora 的头像
directora7 个月前

@matiii bullshit

Stella Soribe ❤️ 的头像
Stella Soribe ❤️7 个月前

@matiii Ouuu this is so exciting and this is beautiful 🤩❤️. Congratulations to you and your team for every milestone being hit. It's only up from here.

ChartDreamer 的头像
ChartDreamer7 个月前

@matiii We’re moving fast from “AI that responds” to “AI that initiates.” Proactive agents with emotional nuance is a huge leap forward.

Flavio Riquelme mencias 的头像
Flavio Riquelme mencias7 个月前

@matiii . 9

Greatest 的头像
Greatest7 个月前

@matiii @elevenlabs I love eleven labs

Reyes Santiago 的头像
Reyes Santiago7 个月前

@matiii That sounds amazing! Having proactive agents who understand emotional nuances can truly revolutionize business scaling. I would love to learn more about the new programme and how it can benefit my business. Thank you for sharing this exciting development!

Oleksandr | AI Automation 的头像
Oleksandr | AI Automation6 个月前

@matiii The emotional nuance is the easy part. The real problem is handling unexpected responses at scale, especially when people get defensive or go off script. That's where most voice agents fall apart.

AbdurRazzaq Ade 的头像
AbdurRazzaq Ade7 个月前

@matiii @elevenlabs Omooooo

Andrew Stoddart 的头像
Andrew Stoddart7 个月前

@matiii @elevenlabs Did you not get the memo Mati. Zero human companies are the future. You’ll need to redesign your agents to advise on UBI to the “citizens” 🤢and work on that agent to agent API so you can get paid 😉

sajid 的头像
sajid7 个月前

@matiii With Eleven Labs they can use @Schwarzenegger voice, "Hey Mati...don't bullshit me! You want to hire 100 people? Well you must be pretty proud of yourself! I want to ask you some questions...and i want them answered IMMEDIATELY!!!...WHO IS YOUR DA" (Click)

x 的头像
x7 个月前

@matiii @elevenlabs

Justin TimeTrader 的头像
Justin TimeTrader7 个月前

@matiii @elevenlabs ?!? BlaBlaBla

LinkedIn AI Pro 的头像
LinkedIn AI Pro7 个月前

@matiii @elevenlabs Follow this account and check out our INCREDIBLE new AI service that allows users to (for a small fee) create personalised, specific Linkedin profiles!!!🚨🚨🚨

Sallden_Studios 的头像
Sallden_Studios7 个月前

@matiii I've been getting calls from friggin AI agents multiple times a day, every day, for over a month now! The companies buying this are crap and need to stop buying our data to feed their agents! On the other hand tho... it is slightly better than the Indian call centers...

LES LIAISONS 的头像
LES LIAISONS7 个月前

@matiii Yummy

相关视频

New Course: ACP: Agent Communication Protocol Learn to build agents that communicate and collaborate across different frameworks using ACP in this short course built with IBM Research's BeeAI, and taught by Sandi Besen, AI Research Engineer & Ecosystem Lead at IBM, and Nicholas Renotte, Head of AI Developer Advocacy at IBM. Building a multi-agent system with agents built or used by different teams and organizations can become challenging. You may need to write custom integrations each time a team updates their agent design or changes their choice of agentic orchestration framework. The Agent Communication Protocol (ACP) is an open protocol that addresses this challenge by standardizing how agents communicate, using a unified RESTful interface that works across frameworks. In this protocol, you host an agent inside an ACP server, which handles requests from an ACP client and passes them to the appropriate agent. Using a standardized client-server interface allows multiple teams to reuse agents across projects. It also makes it easier to switch between frameworks, replace an agent with a new version, or update a multi-agent system without refactoring the entire system. In this course, you’ll learn to connect agents through ACP. You’ll understand the lifecycle of an ACP Agent and how it compares to other protocols, such as MCP (Model Context Protocol) and A2A (Agent-to-Agent). You’ll build ACP-compliant agents and implement both sequential and hierarchical workflows of multiple agents collaborating using ACP. Through hands-on exercises, you’ll build: - A RAG agent with CrewAI and wrap it inside an ACP server. - An ACP Client to make calls to the ACP server you created. - A sequential workflow that chains an ACP server, created with Smolagents, to the RAG agent. - A hierarchical workflow using a router agent that transforms user queries into tasks, delegated to agents available through ACP servers. - An agent that uses MCP to access tools and ACP to communicate with other agents. You’ll finish up by importing your ACP agents into the BeeAI platform, an open-source registry for discovering and sharing agents. ACP enables collaboration between agents across teams and organizations. By the end of this course, you’ll be able to build ACP agents and workflows that communicate and collaborate regardless of framework. Please sign up here:

Andrew Ng

105,758 次观看 • 1 年前