Build an Elixir Phoenix Channels Voice Agent with a LiveView UI
Combine Phoenix Channels for streaming audio frames with LiveView for the chat UI. BEAM concurrency means one node can hold tens of thousands of voice sessions.
Everything on voice and chat AI agents — real-time speech processing, telephony and phone-system automation, conversational AI, voice UX design, and production deployment.
From the blog
Combine Phoenix Channels for streaming audio frames with LiveView for the chat UI. BEAM concurrency means one node can hold tens of thousands of voice sessions.
The US hair-salon industry is $60B with 1.07M businesses. Houston salons run 35-60% no-show on cancellations within 24h. GlamBook + AI voice agent fixes that with GB-YYYYMMDD-### references.
Meta's 2026 messaging API gets calling, native verification badges, and deprecates Message Tags. Here is the migration map for chat agents.
Wire ElevenLabs Conversational AI to an Express server, expose a public agent over WebSocket, and trigger client tools — full TypeScript tutorial for 2026.
The February 2024 FCC ruling made AI-generated voice calls 'artificial' under the TCPA. The September 2024 NPRM proposes mandatory AI disclosure. Here is the 2026 state of play and what your agent must say.
Modern CCaaS desktops are WebRTC under the hood. Here is how Glia, Talkdesk, and LivePerson use it — and how CallSphere plugs an AI agent into the same socket.
FCM high-priority + Telecom CallsManager is the Android equivalent of PushKit + CallKit for AI voice. Here is how to ship it without losing future push priority.
1-800-FLOWERS is iconic for a reason: 72% of people remember vanity numbers after hearing them in ads versus 5% for random digits. Here is how to provision a vanity DID, route it to an AI receptionist, and measure the lift.
67% of lost sales come from bad lead qualification. AI voice slashes call cost from $7-12 to $0.40 and gives agencies a brand-new productized SKU at 75% margin.