The Hunt for Robust Computer Use Agents with Angelo Giacco

Описание: Foundational audio models are reshaping how humans interact with machines. Voice interfaces are becoming more natural, expressive, and deployable at global scale.

In this live demo-talk, Angelo Giacco from ElevenLabs walks through the current state of audio AI, showing how large-scale text-to-speech, speech-to-text, and agentic voice systems are being built, scaled, and shipped in production. From emotional speech control to real-time transcription and AI voice agents, this session offers a behind-the-scenes look at what it takes to make voice the next major interface for technology.

02:35 Scaling laws for audio: control over intelligence
04:41 Text-to-Speech V2 vs V3: emotion & controllability
05:44 Prompting voice with emotions, sound effects & accents
07:42 Speech-to-Text at scale: Scribe Realtime V2
09:02 Accidental discovery of music generation models
11:13 Voice AI in games: live conversational characters
12:02 Running voice at massive scale (Fortnite case study)


Thank you to all our partner to make this happen! A big thanks to our gold sponsors for believing in us:

Uphold:
Founded in 2013, Uphold is a digital wallet and trading platform that makes cryptocurrencies and other assets affordable and accessible to everyone.
With coverage of 300+ assets, Uphold allows users to move seamlessly between digital and traditional currencies, enabling borderless access to financial services you can’t get through your bank. Their Anything-to-Anything interface lets anyone fund, trade, or send money globally in just one tap. Check it here: https://uphold.com

Datalinks:
DataLinks recognizes the importance of nurturing the AI ecosystem. They bring ontologies and knowledge graphs to Lisbon AI, redefining data engineering and shaping the future of Agentic Workflows and Vertical Search.
Discover how scattered data can be unified and linked to power your agents and backends, all with a single click and some prompts: https://datalinks.com/

Follow Angelo:
https://x.com/giaccoangelo

Follow ‪@elevenlabsio‬ :
https://x.com/HuggingFace

Follow us on X:
https://x.com/lisbonai_

Follow us on LinkedIn:
  / lisbon-ai  

Opening music:
‪@NIN‬