We’ve moved past the era of simply typing into a chat box. AI now has a voice, and it’s becoming almost imperceptible from human interaction. In this episode⁠⁠, ⁠James Gauci⁠ and ⁠⁠⁠Llew Jury ⁠ dive deep into the "Holy Trinity" of Voice AI: Cloning, Orchestration, and Connectivity.From the strategic decision of using open-weight models like Qwen to the real-world risks of voice deepfakes, we cut through the hype to show you how to build a sovereign and secure voice stack.

Inside this episode:

• 🛠️ The Voice Tech Stack: Why James is testing Pipecat and Qwen2-Audio for ultra-low latency.

• ⚖️ Platform vs. Open Source: Comparing the ease of ElevenLabs and Vapi against the security of self-hosting.

• 🚫 The Death of Voice Authentication: Why 3 seconds of audio is enough to clone a voice and what it means for your business security.

• 👤 Human in the Lead: The importance of guardrails, ethics, and informed consent in AI deployments.

• 🌍 Geopolitics & The Cloud: A look at how recent events in the Middle East and the US impacted AWS and Anthropic.

  
  

🧪 Featured Tools & Frameworks:

• ElevenLabs
• Vapi
• Aircall
• Pipecat
• Qwen
• Gemini 1.5 Flash

Connect with the Hosts:

• ⁠⁠⁠James Gauci:⁠⁠⁠ CEO of Cadent.

• ⁠⁠⁠Llew Jury:⁠⁠⁠ Managing Director of Advancer at the AI Agency.

• ⁠⁠⁠Zero Shot:⁠⁠⁠ Follow us on LinkedIn for clarity in a complex landscape.

🤠 Sponsor: This episode is brought to you by ⁠⁠⁠⁠Prompt Cowboy⁠⁠⁠⁠—the fastest way to turn everyday business into automated workflows. They wrangle the hard stuff so you can focus on what matters. Visit promptcowboy.ai to start saving time today.

Produced by Yennia La Rotta.⚡