---
title: "Gemini 3.8 Live for Voice Agents: Latency, Price per Minute, and When to Leave Twilio"
description: "Google shipped gemini-3.8-live and Live Extended Thinking on 15 September 2026, native speech-to-speech at about $0.005 / $0.018 per minute. Here is how it changes a production voice stack."
image: "https://foundrysoft.co/images/blog-cards/gemini-3-8-live-voice-agent-latency-pricing.png"
url: "https://foundrysoft.co/blog/gemini-3-8-live-voice-agent-latency-pricing"
---

Tutorial // Voice 2026-09-17 11 min read

# Gemini 3.8 Live for Voice Agents: Latency, Price per Minute, and When to Leave Twilio

Google shipped gemini-3.8-live and Live Extended Thinking on 15 September 2026, native speech-to-speech at about $0.005 / $0.018 per minute. Here is how it changes a production voice stack.

![Varun Raj Manoharan](https://foundrysoft.co/images/about/founder.webp)

Varun Raj Manoharan Founder & Principal Engineer

Gemini Voice AI Agents Customer Support Cost Optimization

## Key takeaways

-   Gemini 3.8 Live is a native speech-to-speech Live API SKU (plus an Extended Thinking variant), not another Flash chat model. List audio rates are about $0.005/min in and $0.018/min out.
-   The win is killing the STT to LLM to TTS hop. If your p95 time-to- first-audio is already under 400ms on a tuned pipeline, the product win is smaller than the migration cost.
-   Telephony is still a transport problem: SIP, barge-in, hold music, PCI, call recording. Live does not replace Twilio or your CCaaS.
-   Background tool calls during speech are the feature to design for. If the agent cannot look up an order while it is talking, you have a demo.

## In this article

1.  01 [What changed in the architecture](#what-changed-in-the-architecture)
2.  02 [Price per minute, not per million tokens](#price-per-minute-not-per-million-tokens)
3.  03 [When to leave the three-hop stack](#when-to-leave-the-three-hop-stack)
4.  04 [Design rules we would ship with](#design-rules-we-would-ship-with)
5.  05 [Frequently Asked Questions](#frequently-asked-questions)

Google shipped `gemini-3.8-live` and `gemini-3.8-live-extended-thinking` on 15 September 2026. Native speech-to-speech, Live API, listed around $0.005 per minute input and $0.018 per minute output, with background tool calls while audio is in flight. Distinct from Gemini 3.8 Flash (chat/coding) and from 3.5 Transcribe.

If you have been assembling voice agents from Whisper or Deepgram, a chat model, and ElevenLabs or Cartesia, this is the first generally pitched SKU in months that makes "delete the three-hop pipeline" a serious option. It is not automatic, and it is not a reason to rip out telephony.

For the older Omni Flash path, see [building a sub-second voice agent](https://foundrysoft.co/blog/gemini-omni-flash-realtime-voice-agent). For turn-taking physics, see [voice agent latencies and WebRTC](https://foundrysoft.co/blog/voice-agent-latencies-webrtc-turn-taking).

## What changed in the architecture

Classic hop:

1.  Stream audio to STT (200 to 500ms)
2.  Wait for LLM first token (400 to 1200ms)
3.  Stream TTS (200 to 400ms)

Best case you are still over a second of dead air. Users say "hello?" and the agent double-talks.

Live SKUs take raw audio in and raw audio out. Tool calls can run in the background so the model does not have to stop speaking to fetch an order. Extended Thinking is the variant that is allowed to pause longer when the lookup is actually hard. Use it on collections and claims, not on "what are your hours."

## Price per minute, not per million tokens

Voice invoices in minutes. At $0.005 in and $0.018 out, a five-minute support call with roughly equal talk time is on the order of $0.06 for model audio, before telephony, recording, and tools.

Compare that to a three-hop stack:

-   STT: often $0.006 to $0.015 / min
-   LLM: highly variable; a chatty agent can blow past $0.05 / min in tokens
-   TTS: $0.015 to $0.04 / min depending on the voice

Live can win on the model line. It does not win if you still pay Twilio for the leg, still record for QA, and still run a separate LLM for after-call summary. Add those up before you tell finance the voice bot is now "two cents a call."

## When to leave the three-hop stack

**Move a route to 3.8 Live when:**

-   Time-to-first-audio is your actual complaint, not NLU accuracy
-   The conversation is English-first (97-language switching is marketed; verify the languages you care about on a real call)
-   Tools are few, well typed, and safe to run while the caller is listening
-   You can accept Google as the voice brain for that line of business

**Keep STT plus LLM plus TTS when:**

-   You need a specific branded voice that Live cannot match
-   Compliance requires a transcript you already trust from a named STT vendor
-   The agent must run on a model Google does not host (Opus 5 on the language, Live only on the mouth: possible, but you are back to hops)
-   PCI or healthcare recording rules make a new audio data-flow a legal project, not a sprint

Telephony stays. SIP trunks, DIDs, queueing, warm transfer, and "press 1" are not Gemini features. Live is the brain and the mouth. Twilio, LiveKit, or your CCaaS is still the wire. See [voice agent latency on telephony](https://foundrysoft.co/blog/voice-agent-latency-telephony-websocket-guide).

## Design rules we would ship with

1.  **Barge-in first.** If the caller talks over the agent and the agent keeps going, you will get one-star calls. Test this on day one, not after the demo.
2.  **Tools in the background, results in the next sentence.** "I am pulling that up" is allowed. Silence is not.
3.  **Extended Thinking only on a named intent.** Default Live for greetings and FAQs. Thinking for exceptions. Otherwise you pay latency on every turn.
4.  **Transcript anyway.** Even if you do not use STT in the loop, persist a transcript for QA and evals. You cannot improve what you cannot read.
5.  **Shadow, then cut over one queue.** IVR FAQ first. Password reset second. Never the collections line first.

## Frequently Asked Questions

**Is 3.8 Live the same as 3.8 Flash?** No. Flash is a text/agent coding SKU. Live is speech-to-speech. Do not put Flash on a phone call and do not put Live on a code-review agent.

**Can we keep our ElevenLabs voice?** Then you are not on native Live output. You can still use Live for understanding and a separate TTS for the mouth, but you have reintroduced a hop. Measure it; do not assume it is "almost as fast."

**What about EU and India data residency?** Confirm where audio is processed and stored on the Live API before you point a European or Indian number at it. Voice is personal data. The SKU launch does not answer that for you.

**How do we eval a voice agent?** Text evals on transcripts plus a latency budget (p50 and p95 time-to-first-audio, barge-in success rate, talk-over rate). If you only score the transcript, you will ship a polite agent that feels drunk on the phone.

---

_FoundrySoft builds production voice agents with real telephony, not just a browser mic demo. See [AI voice agents](https://foundrysoft.co/services/ai-voice-agent) or [get in touch](https://foundrysoft.co/contact)._

Interactive Engineering Calculators Free Tools

### Estimate your project cost, token budget, and automation ROI

We built free, production-calibrated tools to help engineering leaders forecast token consumption, compare build vs buy scenarios, and audit code security.

[Automation ROI Calculator →](https://foundrysoft.co/tools/automation-roi) [Project Cost Estimator →](https://foundrysoft.co/tools/project-cost-estimator) [Build vs Buy Calculator →](https://foundrysoft.co/tools/build-vs-buy) [Security Code Audit →](https://foundrysoft.co/tools/code-audit)

#### Work with us on this

[OpenAI Integration Services

Secure, scalable LLM integration services. We embed current OpenAI and Anthropic models into your existing enterprise software, with the provider abstraction that lets you switch later.

](https://foundrysoft.co/services/openai-integration-services)[Vercel AI SDK Multimodal Processing

Extend your applications beyond text. We implement the Vercel AI SDK's multimodal capabilities to process images, video, and audio natively.

](https://foundrysoft.co/services/vercel-ai-sdk-multimodal-processing)[AI Voice Agent

Expert AI Voice Agent services by FoundrySoft. We build scalable, secure, and modern solutions tailored to your business needs.

](https://foundrysoft.co/services/ai-voice-agent)

#### Related reading

[ChatGPT Sponsored Agents: Buy Distribution or Keep Building Your Own

OpenAI is testing labeled ChatGPT ads and Sponsored Agents (16 September 2026), with HubSpot and Shopify hooks. Here is when paid distribution inside ChatGPT is a channel, and when it is a trap.

OpenAI AI Strategy AI Agents

](https://foundrysoft.co/blog/chatgpt-sponsored-agents-vs-building-your-own)[Claude Fable 5.1 Cache Pricing: Cut Production LLM Bills Without a Model Swap

Anthropic cut Fable 5.1 cache-read costs 75% on 1 September 2026. Here is who actually saves money, how to structure prompts so the cache hits, and when Opus 5 is still the right spend.

Claude Anthropic Cost Optimization

](https://foundrysoft.co/blog/claude-fable-5-1-cache-pricing-cut-llm-bills)[If Your India Team Cannot Call Claude Fable 5: Export Controls and How to Architect Around Them

US Commerce rules from June 2026 restrict some Anthropic frontier SKUs for foreign-national staff. Here is what that means for a US company with an India engineering bench, and the patterns that still ship.

Claude Anthropic Compliance

](https://foundrysoft.co/blog/claude-fable-5-export-controls-india-engineering-team)

#### Next Article

[

GPT-6 Astra vs Claude Opus 5 vs Gemini 3.1 Pro: Which Model You Can Actually Deploy This Week

](https://foundrysoft.co/blog/gpt-6-astra-vs-claude-opus-5-vs-gemini-3-1-pro)

Available for new projects

## Let's build something great.

Have a project in mind? We are an elite software and AI development studio ready to bring your ideas to production. Let's talk about your roadmap.

Start a Project [See our work](https://foundrysoft.co/work)

```json
{
  "@context": "https://schema.org",
  "@type": "Organization",
  "name": "FoundrySoft",
  "url": "https://foundrysoft.co",
  "logo": "https://foundrysoft.co/logo.svg",
  "description": "FoundrySoft builds production-grade software and AI systems for US companies, from an India-based team of senior engineers.",
  "sameAs": [
    "https://github.com/foundrysofthq",
    "https://www.linkedin.com/company/foundrysoft",
    "https://www.instagram.com/foundrysoft/"
  ]
}
```

```json
{
  "@context": "https://schema.org",
  "@type": "WebSite",
  "name": "FoundrySoft",
  "url": "https://foundrysoft.co"
}
```

```json
{
  "@context": "https://schema.org",
  "@type": "TechArticle",
  "headline": "Gemini 3.8 Live for Voice Agents: Latency, Price per Minute, and When to Leave Twilio",
  "description": "Google shipped gemini-3.8-live and Live Extended Thinking on 15 September 2026, native speech-to-speech at about $0.005 / $0.018 per minute. Here is how it changes a production voice stack.",
  "url": "https://foundrysoft.co/blog/gemini-3-8-live-voice-agent-latency-pricing",
  "mainEntityOfPage": "https://foundrysoft.co/blog/gemini-3-8-live-voice-agent-latency-pricing",
  "image": [
    "https://foundrysoft.co/images/blog-cards/gemini-3-8-live-voice-agent-latency-pricing.png"
  ],
  "datePublished": "2026-09-17",
  "dateModified": "2026-09-17",
  "keywords": "Gemini, Voice, AI Agents, Customer Support, Cost Optimization",
  "author": {
    "@type": "Person",
    "name": "Varun Raj Manoharan",
    "jobTitle": "Founder & Principal Engineer",
    "url": "https://foundrysoft.co/about",
    "sameAs": [
      "https://www.linkedin.com/in/varunrajmanoharan",
      "https://github.com/varun-raj"
    ]
  },
  "publisher": {
    "@type": "Organization",
    "name": "FoundrySoft",
    "logo": {
      "@type": "ImageObject",
      "url": "https://foundrysoft.co/logo.svg"
    }
  }
}
```

```json
{
  "@context": "https://schema.org",
  "@type": "BreadcrumbList",
  "itemListElement": [
    {
      "@type": "ListItem",
      "position": 1,
      "name": "Home",
      "item": "https://foundrysoft.co/"
    },
    {
      "@type": "ListItem",
      "position": 2,
      "name": "Blog",
      "item": "https://foundrysoft.co/blog"
    },
    {
      "@type": "ListItem",
      "position": 3,
      "name": "Gemini 3.8 Live for Voice Agents: Latency, Price per Minute, and When to Leave Twilio",
      "item": "https://foundrysoft.co/blog/gemini-3-8-live-voice-agent-latency-pricing"
    }
  ]
}
```

```json
{
  "@context": "https://schema.org",
  "@type": "FAQPage",
  "mainEntity": [
    {
      "@type": "Question",
      "name": "Is 3.8 Live the same as 3.8 Flash?",
      "acceptedAnswer": {
        "@type": "Answer",
        "text": "No. Flash is a text/agent coding SKU. Live is speech-to-speech. Do not put Flash on a phone call and do not put Live on a code-review agent."
      }
    },
    {
      "@type": "Question",
      "name": "Can we keep our ElevenLabs voice?",
      "acceptedAnswer": {
        "@type": "Answer",
        "text": "Then you are not on native Live output. You can still use Live for understanding and a separate TTS for the mouth, but you have reintroduced a hop. Measure it; do not assume it is \"almost as fast.\""
      }
    },
    {
      "@type": "Question",
      "name": "What about EU and India data residency?",
      "acceptedAnswer": {
        "@type": "Answer",
        "text": "Confirm where audio is processed and stored on the Live API before you point a European or Indian number at it. Voice is personal data. The SKU launch does not answer that for you."
      }
    },
    {
      "@type": "Question",
      "name": "How do we eval a voice agent?",
      "acceptedAnswer": {
        "@type": "Answer",
        "text": "Text evals on transcripts plus a latency budget (p50 and p95 time-to-first-audio, barge-in success rate, talk-over rate). If you only score the transcript, you will ship a polite agent that feels drunk on the phone. --- FoundrySoft builds production voice agents with real telephony, not just a browser mic demo. See AI voice agents or get in touch."
      }
    }
  ]
}
```