Browse older CallSphere articles on AI voice agents, contact center automation, and conversational AI.
From the blog
Insurance brokers and MGAs absorb the FNOL spike when storms hit. Here is how a 2026 AI voice agent takes a structured first notice of loss in 4 minutes and answers binder questions live.
GCP Speech-to-Text Chirp at $0.016 per 15s and Vertex Live multimodal pricing change the math. Where Google Cloud's voice stack beats AWS and OpenAI — and where it does not.
Why a single AI call across state lines can be recorded legally in 38 states and illegally in 12, and the disclosure model that resolves it without breaking the agent's flow.
Your traces are a security exposure. PHI, credit cards, passwords end up in spans, prompts, and tool args. Here's a layered redaction pipeline that runs before export.
Letta treats the LLM like an OS that manages its own RAM, recall, and archival memory. Here is when this paradigm beats simple vector stores.
LiveKit Agents 1.5 (April 2026) added an audio-based interruption model and native MCP tools. Here's a full self-hosted LiveKit voice agent with adaptive turn detection.
Good agent memory needs to forget. Time-decay weights recent memories higher; Ebbinghaus-style curves auto-evict stale entries; TTL tiers keep allergies forever and small-talk for an hour.
Catch out-of-band changes to AI voice infrastructure with Atlantis-driven Terraform PRs, driftctl coverage scans, and a daily \`terraform plan -detailed-exitcode\` cron.
Pre-trained Speech Commands models, ml5.js wrappers, and TensorFlow.js with the WASM/WebGPU backend let you ship a voice agent with wake-word, intent, and tone detection — all client-side.
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.
