Browse older CallSphere articles on AI voice agents, contact center automation, and conversational AI.
From the blog
Build a complete screenshot-action loop where GPT-4V analyzes web pages, decides where to click, and navigates autonomously. Learn coordinate extraction, click targeting, and navigation decision-making.
Implement visual regression testing using GPT Vision to detect UI changes, classify their severity, and generate human-readable reports. Move beyond pixel-diff tools to semantic understanding of visual changes.
Anthropic shipped persistent memory to every Claude tier in March 2026, with siloed Projects memory and a public-beta Managed Agents memory tool.
How to bridge a Twilio Media Streams WebSocket to OpenAI Realtime in production: codec conversion, interruption handling, and the timeouts that actually matter.
LiveKit Cloud is the most-deployed managed SFU for AI voice in 2026. Here is what we learned shipping it next to OpenAI Realtime across CallSphere's six verticals.
Stream microphone audio from a browser to FastAPI, fan out to OpenAI Realtime over WebSocket, and play model audio back — full Python tutorial with PCM16 24kHz.
Dental practices are losing 25-40% of inbound calls. Here is how a 2026 AI voice agent handles eligibility checks, recall, and the reminder cadence that actually drops no-shows.
PCM16 at 24kHz burns 384 kbps. Opus at 32 kbps delivers indistinguishable quality. The bandwidth math says use Opus. The vendor API math sometimes says use PCM16. Here is when each wins.
What attestation level your AI calls actually receive, why Level A is the only one that lights up Caller Verified on the receiver's screen, and how to get there with a Twilio-style trust profile.
Get notified when we publish new articles on AI voice agents, automation, and industry insights. No spam, unsubscribe anytime.
Try our live demo -- no signup required. Talk to an AI voice agent right now.
