Building Reliable Voice Agents with Open Source tools


Large Language Models (LLMs) are great at writing. Behind a chat interface they can chat with users almost like a real human would. But are they able to _talk_ like a human? Voice Agents are LLM-powered applications that can listen to users and talk back to them with a realistic voice, handle interruptions and improvise, while sticking to the goal they're given.

In this session we will learn how they’re made, which open source tools are available to build them, and we are going to see in practice how to build one. Along the way we will see what’s their industry impact today and what are the challenges of bringing a voice agent PoC to production, with some real-world stories from our own journey from a small demo to a large-scale deployment.

Background Knowledge:

Basic Python knowledge is sufficient


Sara Zanzottera is a Lead AI Engineer at Kwal, working on open-source voice agents. Before joining Kwal she was a core maintainer of Haystack, one of the most mature open-source RAG frameworks, leading the design and rewrite of its 2.0 version. She started her career at CERN as a Python software engineer on the particle accelerator’s control systems.

Open Data Science




Open Data Science
One Broadway
Cambridge, MA 02142

Privacy Settings
We use cookies to enhance your experience while using our website. If you are using our Services via a browser you can restrict, block or remove cookies through your web browser settings. We also use content and scripts from third parties that may use tracking technologies. You can selectively provide your consent below to allow such third party embeds. For complete information about the cookies we use, data we collect and how we process them, please check our Privacy Policy
Consent to display content from - Youtube
Consent to display content from - Vimeo
Google Maps
Consent to display content from - Google