By Sagar Shankaran, Founder of CallSphere
The three production-grade native speech-to-speech LLMs of 2026, side by side. Latency, prosody quality, function calling, and where each one breaks.
Key takeaways
Until 2024, voice agents were ASR → LLM → TTS pipelines. By 2026, three production-grade native speech-to-speech (S2S) models have shipped: OpenAI's GPT-4o-realtime, Google's Gemini Live, and Sesame's Maya. Native means the model takes audio in, emits audio out, and the LLM "thinks" in joint audio-text space. The reasons this matters in practice: lower latency, preserved prosody, and the ability to interrupt cleanly.
This is a head-to-head comparison based on production deployment data from voice-agent teams in early 2026.
flowchart LR
subgraph Pipeline[Pipeline 2024]
A1[Audio In] --> ASR --> LLM --> TTS --> A2[Audio Out]
end
subgraph Native[Native S2S 2026]
B1[Audio In] --> M[Multimodal LLM] --> B2[Audio Out]
end
The native architecture eliminates two transcoding steps and the loss-of-prosody problem. Round-trip latency drops from 700-1500ms (pipeline) to 300-700ms (native).
OpenAI's offering, refreshed in early 2026 with the GPT-4o-realtime preview line. It is the most-deployed S2S model in production agents.
CallSphere's healthcare voice agent runs on GPT-4o-realtime in production for this reason — function calling under barge-in is the make-or-break feature.
Hear it before you finish reading
Talk to a live CallSphere AI voice agent in your browser — 60 seconds, no signup.
Google's S2S, integrated into Vertex AI. Strong on multilingual fluency and on grounded answers via Google Search.
Sesame is the dark horse. Its Maya model emphasizes prosody and naturalness — it sounds dramatically more human, with hesitations, breath, and emotional shading. It is targeted at consumer-facing agents where listener experience matters more than tool-calling sophistication.
flowchart TD
Q1{Function-calling-heavy?} -->|Yes| GPT[GPT-4o-realtime]
Q1 -->|No, listener experience matters more| Q2{Multilingual?}
Q2 -->|Yes| Gem[Gemini Live]
Q2 -->|No, English-first<br/>natural feel critical| Sesame[Sesame Maya]
We ran a head-to-head on the same booking-flow scripts across 1500 customer calls per model. Headline numbers (your mileage will vary by use case):
The takeaway is unambiguous: production voice agents that need to actually do things (book, lookup, transact) lean GPT-4o-realtime. Customer-facing brand experiences where the conversation is the product lean Sesame.
Past the high-level view in Speech-to-Speech LLMs 2026: GPT-4o-realtime vs Gemini Live vs Sesame Maya, the engineering reality you inherit on day one is graceful degradation when the realtime model stalls — fallback voices, repeat prompts, and confident "let me transfer you" lines that still feel human. Treat this as a voice-first system from the first prompt: the agent's persona, its tool surface, and its escalation rules all flow from that single decision. Teams that ship fast tend to instrument the loop end-to-end before they tune any single component, because the bottleneck is rarely where intuition puts it.
A production-grade voice stack at CallSphere stitches Twilio Programmable Voice (PSTN ingress, TwiML, bidirectional Media Streams) to a realtime reasoning layer — typically OpenAI Realtime or ElevenLabs Conversational AI — with sub-second response as a hard SLO. Anything north of one second of perceived silence and callers either repeat themselves or hang up; that single number drives the whole architecture. Server-side VAD with proper barge-in support is non-negotiable, otherwise the agent talks over the caller and the conversation collapses. Streaming TTS with phoneme-aligned interruption keeps the cadence natural even when the user changes their mind mid-sentence. Post-call, every transcript is run through a structured pipeline: sentiment, intent classification, lead score, escalation flag, and a normalized slot extraction (name, callback number, reason, urgency). For healthcare workloads, the BAA-covered storage path, audit logs, encryption-at-rest, and PHI-safe transcript redaction are wired in from day one, not bolted on at compliance review. The end state is a system where every call produces a row of structured data, not just a recording.
Still reading? Stop comparing — try CallSphere live.
CallSphere ships complete AI voice agents per industry — 14 tools for healthcare, 10 agents for real estate, 4 specialists for salons. See how it actually handles a call before you book a demo.
How do you actually ship a voice agent the way Speech-to-Speech LLMs 2026: GPT-4o-realtime vs Gemini Live vs Sesame Maya describes?
Treat the architecture in this post as a starting point and instrument it before you tune it. The metrics that matter most early on are end-to-end latency (target < 1s for voice, < 3s for chat), barge-in correctness, tool-call success rate, and post-conversation lead score distribution. Optimize whatever the data flags as the bottleneck, not whatever feels slowest in your head.
What are the failure modes of voice agent deployments at scale?
The two failure modes that bite hardest are silent context loss across multi-turn handoffs and tool calls that succeed in dev but get rate-limited in production. Both are solvable with a proper agent backplane that pins state to a session ID, retries with backoff, and writes every tool invocation to an audit log you can replay.
How does the IT Helpdesk product (U Rack IT) handle RAG and tool calls?
U Rack IT runs 10 specialist agents with 15 tools and a ChromaDB-backed RAG index over runbooks and ticket history, so the agent can pull the exact resolution steps for a known issue instead of hallucinating. Tickets open, route, and close end-to-end without a human in the loop on the easy 60%.
Book a 30-minute working session at calendly.com/sagar-callsphere/new-meeting and bring a real call flow — we will walk it through the live IT helpdesk agent (U Rack IT) at urackit.callsphere.tech and show you exactly where the production wiring sits.
Written by
Sagar Shankaran· Founder, CallSphere
Sagar Shankaran is the founder of CallSphere, where he builds production AI voice and chat agents deployed across healthcare, hospitality, real estate, and home services. He writes about agentic AI, LLM engineering, and shipping voice agents that handle real calls in production.
See how AI voice agents work for your industry. Live demo available -- no signup required.
A founder's guide to texto a voz (text-to-speech in Spanish): LATAM vs Castilian voices, free options, and how CallSphere ships Spanish agents.
A founder's guide to the female voice generator landscape: AI female voices, Japanese voices, robot voices, and how CallSphere ships 57+ voices live.
A founder's guide to the Siri voice generator landscape: how AI voice cloning works, what is legal, and how CallSphere uses 57+ voices in production.
A founder's guide to AI voice assistants for ecommerce: customer service, order lookup, and how CallSphere fits in versus virtual receptionists.
Robot text to speech in 2026: how I pick TTS APIs, when robotic voices help, and how CallSphere ships 57+ language voice agents. Hands-on guide.
The customer support specialist role in 2026 is half human, half AI. Here is what the job looks like, the AI tools that pair with it, and how we ship it.
© 2026 CallSphere LLC. All rights reserved.
Watch how CallSphere handles real customer calls, schedules appointments, and processes payments — live.
Try Live DemoBook a DemoCalculate Your ROI