Build a Voice Agent on Cloudflare Calls + Workers AI (2026)
Build a voice agent that runs entirely on Cloudflare's edge: Calls SFU for WebRTC, withVoice mixin for STT/TTS, Workers AI for inference. No external infra, sub-300ms hops.
11 min read
Voice & Chat Agents
Voice & Chat Agents archive page 30 of 42
Voice & Chat AI Agents
Everything on voice and chat AI agents — real-time speech processing, telephony and phone-system automation, conversational AI, voice UX design, and production deployment.
Latest analysis
Ideas you can put to work
Australia ACMA and the Spam Act for AI Voice Campaigns in 2026
ACMA's 2025-26 priorities for AI voice, the Telemarketing Industry Standard 2017, the Do Not Call Register Act, and the SMS Sender ID Register that takes effect July 1 2026.
10 min read
Voice Agent for Elderly & Accessibility: Designing for Everyone (2026)
Voice interfaces lift task completion 40%+ for users with motor impairments — but only if speech rate, pause budgets, and feedback patterns adapt. We map ADA-aligned UX and CallSphere's senior-friendly mode.
11 min read
Vonage Voice API Media Streaming for AI Voice in 2026: WebSocket Connectors and ElevenLabs
Vonage's WebSocket Voice Connector pipes phone calls into AI endpoints with low overhead, and the prebuilt ElevenLabs Conversational AI integration ships sub-second latency. Here is the 2026 wiring for Vonage-resident teams.
10 min read
ROI of an AI Salon Booking Upsell Engine in 2026
Salon upsell bundles lift average tickets 18-30% and conversational upsells deliver 15-25% transaction-value gains. A $5-$15 per-client increase scales to $24K/year. Here is what the 4-agent salon stack returns.
9 min read
Barge-In and Interruption Detection Metrics for Voice AI in 2026
A voice agent that cannot be interrupted feels like an IVR. One that interrupts itself feels broken. Here is the four-metric framework - barge-in success, false barge-in, missed barge-in, response latency - we use to tune turn-taking.
10 min read
Build a Voice Agent with Hume EVI 3: Emotionally Intelligent Voice (2026)
Hume EVI 3 is one model for STT+LLM+TTS with prosody-aware reactions. Build a customizable speech-to-speech agent — TypeScript code, voice prompting, pitfalls.
12 min read
Canada CRTC and CASL: AI Voice Calls and Consent in 2026
Why CASL applies to AI voice calls the same way it applies to human calls, what express versus implied consent looks like for outbound, and how to keep penalties below the CAD $10M corporate cap.
10 min read
iOS Background Audio Recording for AI Dictation (2026): Survives the Lock Screen
Apple's background audio mode is the only sanctioned path to keep recording when the user locks the iPhone. Here is the 2026 playbook for AI dictation apps.
10 min