Jozef Marko
@Marko_Jozef
Followers
432
Following
1K
Media
19
Statuses
177
ElevenLabs | Agents Platform lead | ex-Google
Zug, Switzerland
Joined October 2014
This is just such a great art piece
Sir Michael Caine joins ElevenReader. His unmistakable voice now joins the platform, marking a new chapter where storytelling meets technology. Learn more and listen in.
0
0
8
Voice agents are going from cool demos to real-world deployments — but making them reliable is still tough. Join us for a conversation with @elevenlabsio Voice Agent Lead, @Marko_Jozef, on how they’re scaling production-ready voice agents. He’ll unpack what’s actually working:
0
1
4
Echo that. E.g. we at Eleven figuring out (only) reliable Customer Support using our Agents Platform. Can't imagine someone would trust agents building and deploying secure Enterprise software. Seems OOM harder task while CS is at 1% of total adoption.
0
0
4
Workflows: Combining deterministic action within agent's robust behaviour on ElevenLabs' Agents Platform
Introducing Agent Workflows. A visual editor for designing conversation flows in Agents Platform. Instead of building all of your business logic in a single agent, Workflows enable you to handle more complex scenarios by routing to specialized Subagents.
0
0
4
Studio 3.0 is now live! We're significantly scaling up the ambitions of what you can do with Studio. Starting with bringing all the best AI audio models into one place for voiceovers and audiobooks
Introducing Studio 3.0 The most advanced AI audio models in a single editor, now with video support: •Voiceovers •Music •Sound Effects •Voice Isolation •Voice Changer Plus new Automatic Captioning, Speech Correction for real-life recordings, and Multiplayer Commenting.
1
1
27
Just wow
Introducing Eleven v3 (alpha) - the most expressive Text to Speech model ever. Supporting 70+ languages, multi-speaker dialogue, and audio tags such as [excited], [sighs], [laughing], and [whispers]. Now in public alpha and 80% off in June.
1
0
7
Building language or role playing app was never easier!
Conversational AI now supports Multivoice mode - letting AI agents switch voice and language mid-sentence. English-speaking agents can say Italian words in a native Italian voice or alternate between characters. Useful for language apps and multi-character audio experiences.
1
0
10
Smoothest voice + text integration
Introducing Multimodal Conversational AI. Starting today, you can talk to our agents using voice and text—simultaneously. It’s fully supported in our SDKs, websocket, and widget. You're now one line of HTML away from launching a multimodal assistant. Fast to deploy.
0
0
7
Imagine being able to fill out a form with your voice—in any language. With Conversational AI this becoming a reality. In this advanced cookbook, you’ll learn how to: - Build an agent that can navigate a @nextjs UI - Collect, analyze, and extract data from conversations - Upload
10
17
183
I'm thrilled to announce that we've reached over 500,000 agents created on our Conversational AI platform! As the lead engineer overseeing this technology, I've witnessed firsthand how conversational AI is transforming critical industries. From healthcare systems that provide
6
12
88
Conversational AI now supports automatic language detection and switching.
16
51
389
RETWEET if you stand with President Zelenskyy against Trump and Vance!
3K
40K
109K
Thank you for your support! 🇺🇦 __ Дякую вам за підтримку! 🇺🇦
24K
33K
365K
From today, @Spotify is now accepting audiobooks narrated by ElevenLabs Voices. More people are listening to audiobooks than ever before. But for many authors, getting an audio version of their work published on major platforms has been expensive and time-consuming — until now.
44
211
2K
Four steps to participate in the worldwide hackathon this weekend: 1. Register online: https://t.co/wJesho4zRV 2. Join the discord: https://t.co/LzmwwqD66T 3. Get hacking. 4. Win prizes.
3
4
51
Inbound conversational AI phone calls can now easily be personalized using @twilio and @elevenlabsio. Provide dynamic variables based on the inbound caller id, and override the prompt, language, first message to fully customize your voice AI agents.
5
4
57
Talk to santa by @louisjoejordan
Say hello to Santa! Our AI Santa lets you chat with the man in red this holiday season. No logins, no barriers—just Santa, ready to swap stories and double-check if you’ve made the nice list this year.
0
0
2
React + JS, Python & iOS sdks available now. Here’s our developer docs to get started: https://t.co/ArL4gm0VEc If you have feedback or feature requests, let me know! Bravo to @i_am_holt @maxilevi__ @aarthificial
elevenlabs.io
Learn how to build, launch, and scale agents with ElevenLabs.
3
3
17
Fortunately, we’ve abstracted away the majority of these technical details so all you need to focus on is the business logic and customization. This means you can spend more time refining your system prompt, choosing a suitable voice, and connecting third party tools with
3
0
8
The turn taking and interruption handling was the hardest challenge to crack. To solve this, we created a real time model of the likelihood that someone is done talking at any moment. If our agent starts talking and the caller continues to speak over them, we have to handle that
2
0
9