·

8/12/2026

Alberto Gonzalez : From SIP to Tokens. Deterministic Telephony Meets Real-Time Voice AI

← Back to schedule

8/12/2026

9:00 am

–

9:30 am

InterContinental Chicago

About the session

This session explores how to safely run real-time Voice AI inside deterministic telephony systems.

We present an open-source production-oriented architecture built on: a SIP edge, FreeSWITCH and a streaming AI pipeline.

FreeSWITCH serves as the deterministic media and call-control layer, enforcing routing rules, timeouts, fallback paths, and session state. Live audio is streamed into an AI pipeline for STT → inference/translation → TTS, with streaming responses injected back into the call.

We will cover:
- Bridging RTP audio into a streaming AI pipeline
- Defining conversational SLOs
- Instrumenting stage-level metrics and visualizing them
- Isolating AI failures and enforcing deterministic fallbacks in real-time telephony.

The session concludes with a live demo of a real-time voice solution running on FreeSWITCH, complete with signaling visibility, media metrics, and AI pipeline timing.

This talk is aimed at engineers building measurable, resilient Voice AI systems on open telephony infrastructure.

‍

Date

8/12/2026

Time

9:00 am

–

9:30 am

Format

Speakers

Alberto Gonzalez

Add to Google Calendar Download .ics

Same day

More sessions

August 10, 2026

Coder Games Welcome and Intro to the Day

ClueCon’s version of a hackathon for coders, builders, and everyone in between.

View session →

August 10, 2026

Challenges Work Time

Jump into a challenge or just enjoy the energy, meet other attendees, and see what everyone is building.

View session →

August 10, 2026

Lunch N' Learn: FreeSWITCH

Join us for the FreeSWITCH Lunch n Learn, where we offer a comprehensive introduction to FreeSWITCH. This session covers everything from installation to configuration, providing you with the foundational knowledge you need to effectively use this powerful telephony platform. Our expert instructors will guide you through each step, ensuring you leave with a solid understanding and practical skills. Whether you’re new to FreeSWITCH or looking to refresh your knowledge, this event is the perfect opportunity to enhance your expertise in a supportive and informative environment

View session →

August 10, 2026

Coder Games Afternoon Work Time

One last chance to ship it. Use the afternoon work session to put the final polish on your project before demos and judging begin. This is the time it all comes together or you take a leap and decide to add the feature you probably shouldn’t. Enjoy the chaos before the winners are crowned.

View session →

August 10, 2026

The Prompt Pit: Live Vibe Coding Challenge

The Prompt Pit brings developers on stage for a fast-paced, AI-assisted coding competition during the ClueCon Coder Games. Contestants compete head-to-head through timed challenges, live demos, and audience-driven twists until one builder makes it through the final round.

View session →

August 10, 2026

Final Work Time

Final finishing touches before the judging.

View session →

August 10, 2026

Demos, Judging, and Prizes

Watch the projects come to life during the final demos. Cheer on the builders and support your favorites.

View session →

August 11, 2026

Anthony Minessale: Keynote Presentation. Real-Time Infrastructure Meets AI Intelligence

AI voice is exploding right now and this community has been preparing for this exact moment for twenty years. We already cracked the brutally hard problems: sub-second latency at scale, media that never breaks, conversational state that survives reality, and infrastructure that stays rock-solid under fire. Those solutions are the foundation production AI voice actually needs. In this keynote, Anthony Minessale shares how the builders behind FreeSWITCH and SignalWire are combining that battle-tested platform with modern AI, so we can all ship intelligent systems faster and more reliably. The smartest teams in the room aren’t starting the real-time stack from scratch. They’re standing on mature infrastructure so they can focus their firepower on the intelligence, the agent experiences, and the breakthroughs that will define the winners. This is our category to win. Just like the great platforms before us (Linux, databases, the web), the biggest victories come when builders choose leverage and ship together instead of diluting effort on the plumbing. Everyone in this room is part of building what comes next, and the teams that move fastest on top of proven foundations are the ones who will own the future.

View session →

August 11, 2026

Kishor Patil: Securing Agentic Workflows at Enterprise Scale

As AI agents move from prototype to production, enterprise teams face new security challenges: trust boundaries between agents, secret sprawl, lateral movement risks, and compliance gaps. This session shares real-world patterns for enforcing Zero-Trust principles, securing service-to-service communication, and building auditable multi-agent systems — with practical takeaways attendees can apply immediately to their own architectures.

View session →

August 11, 2026

Demo/Break

It's your time to take a break and grab a cup of coffee, ask the morning speakers your questions, or attend one of our AI voice demos.‍‍

View session →

August 11, 2026

Brian West: Every voice AI demo ends at deployment. This one starts after the call.

In this live demo, Brian West shows how SignalWire’s post-conversation payload turns a completed Voice AI session into a full operational timeline. Using real open-source demos like GoAir and Holy Guacamole, he walks through the JSON payload generated at the end of a call and shows how it can be used to inspect transcripts, response timing, ASR, LLM, and TTS latency, barge-in behavior, SWAIG function calls, global_data snapshots, and state changes across the entire conversation. The demo also introduces the open-source PostPrompt Viewer, a visual tool for analyzing completed Voice AI calls. Attendees will see how teams can turn raw post-call payloads into practical observability metrics like P95 latency, barge-in rate, tool execution overhead, and response verbosity. A transcript tells you what happened on a call. SignalWire’s post-conversation payload helps show why it happened, where time was spent, and how the AI moved through the conversation. This is what carrier-grade Voice AI observability looks like after deployment.

View session →

August 11, 2026

Luca Pradover - AI Privacy, Security and Best Practices

This session provides a practical overview of how to build and govern AI systems safely, covering: AI governance and ISO/IEC 42001 — the basics of managing AI risk systematically GDPR and the EU AI Act — what US and international technology companies need to know Privacy by design — data minimization, retention, RAG, logging, and vendor considerations AI-specific security risks — prompt injection, sensitive data disclosure, and excessive agency Secure AI architecture — least privilege, deterministic authorization, isolation, validation, and human approval Practical best practices for deploying LLMs and AI agents safely in production

View session →

August 11, 2026

Devang Sharma: The Agentic Shift. Designing Multi-Agent Systems That Actually Work in Production

2026 is the year AI agents move from demos to production, but most multi-agent systems still fail in the wild. This talk dives deep into the architectural patterns, orchestration frameworks, and engineering principles behind reliable agentic systems. We'll explore tool use, memory, planning loops, and inter-agent communication, alongside the often-overlooked challenges of observability, cost control, and failure recovery. Expect real-world case studies, anti-patterns to avoid, and a practical blueprint for building agents that ship.

View session →

August 11, 2026

Lunch N' Learn: Kamailio: SIP Registrar Scalability And Redundancy

The registration is one of the basic functions in SIP, a user agent has to register with a SIP server in order to receive calls or messages. This session focuses on Kamailio components and features that enable vertical or horizontal scalability, contacts replication as well as fine tuning REGISTER requests processing for specific use cases such as fixed or mobile environments, NAT traversal or large number of active subscribers.

View session →

August 11, 2026

Julien Chavanton: FreeSWITCH's improved elastic jitter buffer

Reduce latency and packet loss in audio streams when dealing with jitter over unreliable networks. FreeSWITCH's improved elastic jitter buffer system.

View session →

August 11, 2026

Liviu Chircu: OpenSIPS 4.0 Under the Hood

OpenSIPS 4.0 introduces some of the most significant architectural changes in recent years. This session takes a deep technical look at the new internals and operational capabilities now available to SIP platform engineers. Topics include the redesigned TCP/TLS subsystem, realtime profiling and observability tooling, PRACK/UPDATE interworking, bond sockets, Proxy Protocol support and improvements targeting modern distributed SIP deployments.

View session →

August 11, 2026

Bhavya Raoulji: Using AI to Improve Reliability and Scale in Real-Time Communications

The telecommunications and real-time communications industry operates under strict latency, availability, and reliability requirements. Even small performance issues can lead to dropped calls, poor audio quality, or service outages. This talk focuses on how AI can be practically applied within real-time communication systems (VoIP, messaging, and event-driven platforms) to improve system stability and operational efficiency. It explores real-world approaches to using AI for anomaly detection, traffic prediction, intelligent alerting, and automated scaling without disrupting critical real-time workflows. Key topics include: AI-driven detection of call quality degradation and traffic anomalies Predictive insights for handling peak load and sudden traffic spikes Intelligent observability using metrics, logs, and traces Automating operational decisions while maintaining low latency and high availability Lessons learned from applying AI in production telecom environments Attendees will gain actionable insights into how AI can enhance not replace core engineering practices in real-time communication platforms.

View session →

August 11, 2026

Demo/Break

It's your time to take a break and grab a cup of coffee, ask afternoon speakers your questions, or attend one of our AI voice demos.‍

View session →

August 11, 2026

Shane Harrell: Demo: cat support_engineering | uniq

Support at SignalWire has developed a platform integrated with AI that allows for unparalleled data retrieval and analysis which greatly reducing response times for our customers.

View session →

August 11, 2026

Jeff Pulver: What voice ai needs from telecom in order to live to its potential and how vcons fit in

What voice ai needs from telecom in order to live to its potential and how vcons fit in

View session →

August 11, 2026

Joseph Montes: Making a Class 4/Class 5 environment using FreeSwitch w/ SW

.

View session →

August 12, 2026

Alberto Gonzalez : From SIP to Tokens. Deterministic Telephony Meets Real-Time Voice AI

This session explores how to safely run real-time Voice AI inside deterministic telephony systems. We present an open-source production-oriented architecture built on: a SIP edge, FreeSWITCH and a streaming AI pipeline. FreeSWITCH serves as the deterministic media and call-control layer, enforcing routing rules, timeouts, fallback paths, and session state. Live audio is streamed into an AI pipeline for STT → inference/translation → TTS, with streaming responses injected back into the call. We will cover: - Bridging RTP audio into a streaming AI pipeline - Defining conversational SLOs - Instrumenting stage-level metrics and visualizing them - Isolating AI failures and enforcing deterministic fallbacks in real-time telephony. The session concludes with a live demo of a real-time voice solution running on FreeSWITCH, complete with signaling visibility, media metrics, and AI pipeline timing. This talk is aimed at engineers building measurable, resilient Voice AI systems on open telephony infrastructure.

View session →

August 12, 2026

Brian West: Shut Up and Ship: What Carrier-Grade Voice AI Actually Looks Like

The AI voice agent space is drowning in noise. 10,000+ LinkedIn posts a month, almost none showing architecture. This talk draws a hard line between demo-grade and carrier-grade. I'll walk through SignalWire's three-layer AI Agent control plane: typed functions, state machines, and prompts, and why collapsing them into a single system prompt is the root cause of every production failure nobody posts about. I'll introduce System Directed AI, the architectural principle that separates code-driven business decisions from AI-driven conversational decisions, and show a concrete System Directed AI technique: zero-argument tool calls that read from validated stored state instead of letting the LLM re-supply data on every call. Fewer arguments, fewer failures, guaranteed consistency. Everything shown is open source at https://github.com/signalwire-demos. No demos, no happy-path videos. Just architecture, code, and the failure modes the industry skips.

View session →

August 12, 2026

Abhi Desai: Agents at Scale for Marketing - Troubleshooting with AI Reasoning

Real time systems generate a constant stream of events, yet most AI models are still designed to run offline and produce reports rather than actions. This gap between prediction and decision is where many production systems fail. Developers often have accurate models but no safe, reliable way to use them in live environments. This talk focuses on how to design AI driven decision systems that act on live events with low latency and high reliability. It explains how models connect to event streams, APIs, and rule engines, and how decisions flow through real software systems. The emphasis is on architecture and system behavior rather than algorithms or math. Using real examples from large scale retail and marketing platforms, the session highlights common failure modes such as delayed signals, noisy data, unstable actions, and lack of explainability. It then shows practical design patterns like guardrails, decision thresholds, rollback strategies, and continuous monitoring that allow AI systems to operate safely in production. The ideas and patterns discussed translate directly to WebRTC, telephony, and real time communication systems where decisions such as routing, prioritization, or optimization must happen quickly and predictably. Attendees will leave with a clear reference architecture and practical guidelines they can apply to their own real time systems.

View session →

August 12, 2026

Demo/Break

It's your time to take a break and grab a cup of coffee, ask morning speakers your questions, or attend one of our AI voice demos.‍

View session →

August 12, 2026

Justin Massey: Demo - Building an AI voice agent that answers real customer calls while staying provably on-script.

LLMs are great conversationalists, but can be terrible rule-followers. Point one at a customer call and it'll happily chat, but skip the questions you actually need answered, ask them out of order, or invent a path through your call flow you never intended. Old-school IVR solved determinism by removing the conversation entirely. That's not the trade we want to make. In this live demo, I'll build an AI voice agent that answers real customer calls while staying provably on-script. You'll see how to constrain an LLM so it collects every required piece of information, asks the right questions at the right moments, and honors your call tree, without collapsing back into a rigid "press 1 for support" menu. The agent still improvises, handles interruptions, and sounds human;it just does so inside guardrails you define.

View session →

August 12, 2026

Alex Balashov: Navigating AI and open-source with sanity

The last year has seen a tremendous amount of change in the world of LLMs ("AI"), some good, a good bit of it bad. The year of Claude Code has also reverberated throughout open-source projects, giving developers an unwelcome taste of the societal and occupational impact of LLMs. This potpourri presentation will digest the most important takeaways: what's possible, what's new, and most vitally, what not to do. It will touch on open-source slop PRs, local models, GPU rental, vibe coding, tokenmaxxing, and much more.

View session →

August 12, 2026

Raghavendra Bagalkoti: AI Cloud Economics. Controlling Infrastructure Costs and Maximizing ROI

As enterprise AI deployments mature from experimental pilots to mission-critical applications, managing the associated cloud infrastructure costs has become a top priority for the C-suite. Explore how organizations are balancing aggressive AI innovation with sustainable cloud spending. Discuss strategies for forecasting compute costs, optimizing cloud resource allocation, and proving the business ROI of their infrastructure investments. Discover how to architect a cloud strategy that scales your AI capabilities without breaking your budget.

View session →

August 12, 2026

Lunch and Lunch-n-Learn: The new SignalWire SDK changes how you build real-time apps

Grab some lunch and join the SignalWire Lunch-n-Learn: Session abstract: The new SignalWire SDK changes how you build real-time apps — less wiring up event handlers, more describing what you want and reacting to state as it changes. This session is a working tour of it, from first import to a call with multiple participants and a working device picker. We'll start with the shape of the SDK and the mental model behind it, then move through the pieces you'll touch in every project: authenticating properly, addressing the thing you want to reach, managing a call and the people in it, and dealing with the messy reality of microphones and cameras. Bring a laptop if you want to follow along.Agenda: SDK Overview — what's in the package, what changed, and the mental model to hold onto while you use it. Observable State — the SDK surfaces state as observable streams instead of scattered callbacks. Why that's a better fit for real-time, and how to consume it without fighting the grain. Authentication — how tokens work, what your backend is responsible for, and the mistakes that bite people in production. Using Addresses — addresses as the unit of "the thing I want to reach." Looking them up, listing them, and dialing them. Calls and Participants — starting a call and handling the participant lifecycle: joins, leaves, mutes, and everything that happens out of order. Device Management — enumerating mics, cameras, and speakers, switching mid-call, and surviving permissions and hot-plugging.

View session →

August 12, 2026

Hector Zelaya: eBPF Makes Python a Good Language for a TURN Server

TURN servers are a crucial element in any real-time communication that attemps to ensure communication in complex network setups, which also makes them a bottleneck. One particular element contributing to this bottleneck is packets traversing multiple network layers in the operating system. eBPF provides with the ability to run custom code, securely, at the Linux kernel level, providing a way to bypass the user space entirely and boosting the performance of this crucial component

View session →

August 12, 2026

Daniel-Constantin Mierla: Safe and secure communications with Kamailio

In a world where all the public data flowing around is collected and AI-based tools increased the capacity of bad actors to launch attacks, this presentation looks at the components Kamailio offers to run it as a security guardian for VoIP and telephony platforms and the capabilities to ensure the privacy and confidentiality between end users and operator core networks.

View session →

August 12, 2026

Ruchir Brahmbhatt: Whispering in the Agent's Ear. Real-Time Agent Assist on a Live Call

We put real-time transcription and a language model into a live call's media path to assist agents. This talk covers the architecture — media forking, streaming speech-to-text, model-driven suggestions — the latency war that decides whether any of it is usable, and the honest list of things that didn't work.

View session →

August 12, 2026

Hari Kishan: Contact center as a service with GenAI

Contact Centers are moving beyond traditional IVR menus and scripted chatbots. The modern conversational platforms can understand intent, accessing enterprise systems, adding emotions to the response etc. In this session, I will share how we built expressive Voice experience that adds tone, emotions, pacing, conversational personality to contact center bot making interactions significantly more human. We will also touch examine next gen speech to speech frontiers that can listen, reason, handle interruptions, provide backchannel responses, execute tools during live conversation. But when machines become more human, trust becomes more important than realism. We will explore practical governance for enterprise Voice AI including caller disclosure, consent based Voice Cloning, VoiceBiometrics, Prompt injection protection, PII handling, synthetic audio, digital resurrection etc. The future of contact centers is not simply automation. It is building Voice experiences that are expressive, intelligent secure, transparent and trustworthy.

View session →

August 12, 2026

Demo/Break

It's your time to take a break and grab a cup of coffee, ask afternoon speakers your questions, or attend one of our AI voice demos.‍

View session →

Panels & Roundtables

August 12, 2026

Roundtable: Is AI Voice Ready for the Real World?

AI voice is moving fast, but production is a very different test than a polished demo. Real-world voice applications have to handle latency, interruptions, call transfers, unreliable networks, legacy telecom systems, compliance requirements, and human escalation without breaking the experience. This roundtable will explore what it really takes to make AI voice work beyond the demo, from infrastructure and architecture to interoperability, reliability, and trust. Panelists will discuss where AI voice is working today, where it still falls short, and what builders need to solve next to make real-time AI communication ready for production.

View session →

August 13, 2026

Rita Lopes: When Your Network Calls You Back: AI-Driven Voice Alerting with HOMER11

Homer 11 is a major leap forward for VoIP monitoring — faster, more scalable, and smarter. This session takes a fast, practical look under the hood: the architectural changes driving major performance and throughput gains at scale, the new AI-assisted troubleshooting that helps engineers spot anomalies and root causes faster, and the refreshed UI workflows that make day-to-day SIP debugging simpler. And now, you can use Homer from your terminal! Rather than a feature tour, this is a focused look at what changed, why it matters, and how it changes the way you troubleshoot VoIP networks in production. Attendees will leave with a clear, practical understanding of Homer 11’s new capabilities and how to start using them immediately.

View session →

August 13, 2026

Laura Blersch: Unlocking Neurodiversity: Strategies for Strengthening Team Dynamics

Unleash Team Superpowers: A Practical Guide to Neurodiversity in the Workplace. Discover the 'what's in it for me' as you learn to identify and harness the unique strengths of neurodiverse colleagues, including those with Autism, ADHD, and Dyslexia. This session offers practical strategies and interactive exercises to communicate and collaborate with neurodiverse team members effectively. Perhaps your ADHD teammate struggles more with focus at the end of their day, so it might help to schedule your time together in their mornings;you'll gain skills to analyze workplace scenarios and adapt team practices for inclusivity, enhancing overall team dynamics. Leave with a personalized action plan to capitalize on your diverse team's untapped potential and superpowers, boosting innovation and productivity in your professional sphere.

View session →

August 13, 2026

Pavel Oborin: AI and the Future of Cognitive Work. What's Changing, What Remains

AI is automating cognitive work faster than most organisations realise, but the gap between what the technology can theoretically do and what it's actually doing in practice is still enormous. This talk looks at where that gap sits today, what current labour market research says about how it's closing, and which parts of cognitive work are genuinely at risk versus which parts remain distinctly human. Grounded in real deployment experience and recent research, not forecasts.

View session →

August 13, 2026

Pratik Patel: Building the Next-Gen Contact Center with WhatsApp Business Calling and AI

WhatsApp Business Calling now speaks native SIP, letting a WhatsApp number send and receive calls along side chat directly through your own infrastructure. This talk is a field report on combining WhatsApp's Calling API, FreeSWITCH, and AI voice agents into one real, production contact center — covering the actual call path from WhatsApp to your dialplan, the API calls and FreeSWITCH configuration behind it, regional compliance across the US, UK, and EU.

View session →

August 13, 2026

Adam Kalsey: Everyone's Building Voice AI Wrong - and You Already Know the Fix

If you've ever been trapped on the phone with an AI agent that talked over you, went dead silent for six seconds, then handed you to a human who knew nothing about the call you just sat through, then you've heard the problem. What might surprise you is that you already know the solution. You've known it for a decade. Voice AI didn't invent a new class of problem. It resurfaced an old one. Where you put the boundaries between the parts of your system matters. And a whole generation of builders who came from the web are getting it catastrophically wrong, because on the web those boundaries are free and on a phone call they cost you everything. We'll dissect a real, gloriously terrible AI call line by line. We'll do the latency arithmetic that explains why reaching for a bigger model makes things slower and worse. We'll cover the provider failover nobody builds until 3 a.m. on the night it takes them down. You'll leave this talk able to look at any voice agent -- yours or a competitor's -- and know exactly where it's going to break, and what to do about it.

View session →

August 13, 2026

David Duffet: Human Connection in the AI Age - It's all about the BANDWIDTH!

This presentation looks at the importance of 'high bandwidth' human to human connectivity in a business world where AI content and processes are becoming the norm. Get ready to learn 7 Bandwidth Booster to ensure that connection to other humans feels like its a Gigabit fibre connection rather than some sketchy WiFi! Whether you're looking for a promotion at work, your next job in a new company, building the community around your project or even selling your business, there will be something for you!

View session →

August 13, 2026

Lunch N' Learn: Homer

Come see the long awaited Homer 11 in action. VOIP Monitoring in a new skin and stack, based on community feedback and new innovations. And maybe a few small SIP related games for when troubleshooting has become too troublesome.

View session →

August 13, 2026

Dan Christian Bogos: Real-time Billing using CGRateS as External Module via ESL

Modern telecom and VoIP platforms increasingly demand flexible, real-time billing architectures that can scale independently from the switching core. This talk explores how to integrate CGRateS with FreeSWITCH using the Event Socket Library (ESL) to implement externalized, real-time billing and charging workflows. We will walk through the architecture, event flow, and implementation details required to decouple rating logic from the switching layer while maintaining low latency and high reliability. The session covers how CGRateS processes call events in real time, how ESL enables event-driven communication with FreeSWITCH, and how to build scalable charging pipelines for prepaid and postpaid scenarios. CGRateS is a battle-tested Enterprise Billing Suite with support for various prepaid and postpaid billing modes.

View session →

August 13, 2026

Fred Posner: What's new with APIBAN

APIBAN is a free service helping protect your network from unwanted SIP and HTTP traffic. Find out what's new in APIBAN and how we remain FREE (as in beer). Also, what's new with Kamailio?

View session →

August 13, 2026

Dangerous Demos: Hosted by James Body

On the last day of the conference, attendees will go head to head for amazing prizes and bragging rights to be the more elegant, fan favorite demo.

View session →

August 13, 2026

Grand Prize Giveaway and Thanks for Coming!

Put in your raffle tickets to win a one of a kind, custom MacBook!

View session →

Chicago · August 9–12, 2027

See you in the room.

Talks, the Coder Games, and a different Chicago night out every evening.

Register now →