LiveKit Agents vs Gemini
Side-by-side trajectory, velocity, and editorial themes.
LiveKit Agents added Answering Machine Detection — voice agents are becoming a serious telephony runtime.
LiveKit Agents is releasing roughly twice a week along the 1.5.x line, accumulating telephony-grade primitives around its voice loop. The headline is Answering Machine Detection in 1.5.9 — an LLM-classified detector for what kind of endpoint an outbound call hit. Surrounding work is split between reliability (barge-in cooldown, interruption guards, preemptive-generation tuning, observability retries) and provider breadth (Perplexity Responses, Soniox, Speechmatics, Cerebras, xAI, Rime WebSocket TTS). The mcp_servers parameter was also deprecated on Agent and AgentSession.
The product is converging on a real contact-center runtime, not just a realtime meeting agent. AMD, warm transfer, DTMF handling, recording retries, and avatar join/playback metrics are the feature surface phone deployments demand. The provider plugin universe keeps widening; LiveKit positions itself as the neutral broker between voice models and the actual network. Internal cleanups (mcp_servers deprecation, instruction parts, AvatarSession base class) suggest a tidying pass before a 1.6 cut.
Expect more telephony primitives — supervisor barge-in, richer DTMF flows, call-recording controls — and a unified MCP configuration surface across Agent and Session as the mcp_servers deprecation lands fully.
I/O 2026 turns Gemini into an action-taking agent and an omni-modal generator in one breath.
Gemini is mid-I/O announcement burst — almost every recent entry is a release from the May 19 keynote. The headline moves are Gemini 3.5 (frontier model with action support), Gemini Omni (any-input creation/editing in conversational language), an agentic Gemini app with proactive 24/7 behavior, and a new $100/month AI Ultra subscription tier. A sibling Antigravity product and Gemini for Science also debut.
Google is reframing Gemini from "chat assistant" to "agent that takes action across surfaces." The bet is two-pronged: collapse modality boundaries with Omni so users stop choosing between products by input type, and push proactivity so the app pulls work toward you rather than waiting for prompts. Pricing has moved up — a $100 Ultra tier indicates Google now sells Gemini as a premium agent, not a chat companion.
Expect the agentic Gemini app to expand into more third-party actions (booking, purchasing via Universal Cart, scheduling) and for Antigravity to absorb developer-leaning agent workloads. The Ultra tier likely picks up enterprise-style controls in months ahead.
See more alternatives to LiveKit Agents →
See more alternatives to Gemini →