> ## Documentation Index
> Fetch the complete documentation index at: https://docs.getpatter.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Gemini Live

> Google Gemini Live native-audio realtime engine — alternative to OpenAI Realtime.

# Gemini Live

`GeminiLiveAdapter` bridges a bidirectional audio stream to Google's [Gemini Live](https://ai.google.dev/gemini-api/docs/live) native-audio API. It speaks the same `connect / sendAudio / onEvent / close` surface as `OpenAIRealtimeAdapter`, so you can swap engines without touching the call handler.

Use it as an alternative to OpenAI Realtime when you want native-audio Gemini voices, longer context, or lower per-minute pricing.

## Install

Native-audio Gemini Live is a `v1alpha`-only API. Install the optional peer dependency:

<CodeGroup>
  ```bash TypeScript theme={null}
  npm install getpatter @google/genai
  ```

  ```bash Python theme={null}
  pip install "getpatter[gemini-live]"
  ```
</CodeGroup>

Set `GEMINI_API_KEY` in your environment.

## Constructor

<CodeGroup>
  ```typescript TypeScript theme={null}
  import { GeminiLiveAdapter } from "getpatter";

  const adapter = new GeminiLiveAdapter(process.env.GEMINI_API_KEY!, {
    model: "gemini-2.5-flash-native-audio-preview-09-2025",    // default
    voice: "Puck",                                             // Puck | Charon | Kore | Fenrir | Aoede
    instructions: "You are a helpful, concise voice assistant.",
    language: "en-US",
    inputSampleRate: 16000,                                    // PCM16 mono in
    outputSampleRate: 24000,                                   // PCM16 mono out
    temperature: 0.8,
  });
  ```

  ```python Python theme={null}
  from getpatter.providers.gemini_live import (
      GeminiLiveAdapter,
      GeminiLiveModel,
      GeminiLiveVoice,
  )

  adapter = GeminiLiveAdapter(
      api_key="",
      model=GeminiLiveModel.NATIVE_AUDIO_PREVIEW_09_2025,
      voice=GeminiLiveVoice.PUCK,
      instructions="You are a helpful, concise voice assistant.",
      language="en-US",
      input_sample_rate=16000,
      output_sample_rate=24000,
      temperature=0.8,
  )
  ```
</CodeGroup>

## Usage

Pass the adapter as the `engine` on `phone.agent({...})`:

<CodeGroup>
  ```typescript TypeScript theme={null}
  import { Patter, Twilio, GeminiLiveAdapter } from "getpatter";

  const phone = new Patter({ carrier: new Twilio(), phoneNumber: "+15550001234" });

  const agent = phone.agent({
    engine: new GeminiLiveAdapter(process.env.GEMINI_API_KEY!, { voice: "Puck" }),
    systemPrompt: "You are a helpful assistant.",
    firstMessage: "Hi! How can I help today?",
  });

  await phone.serve({ agent });
  ```

  ```python Python theme={null}
  import asyncio
  from getpatter import Patter, Twilio
  from getpatter.providers.gemini_live import GeminiLiveAdapter

  phone = Patter(carrier=Twilio(), phone_number="+15550001234")

  agent = phone.agent(
      engine=GeminiLiveAdapter(api_key="", voice="Puck"),
      system_prompt="You are a helpful assistant.",
      first_message="Hi! How can I help today?",
  )

  asyncio.run(phone.serve(agent))
  ```
</CodeGroup>

Tools work the same way as on OpenAI Realtime — pass `tools: [...]` on `phone.agent({...})` and Patter forwards function calls to Gemini's `functionDeclarations` shape.

## Models

| Model                                                       | Notes                                                            |
| ----------------------------------------------------------- | ---------------------------------------------------------------- |
| `"gemini-2.5-flash-native-audio-preview-09-2025"` (default) | Native-audio preview, `v1alpha` only. Current production target. |
| `"gemini-live-2.5-flash-preview"`                           | Earlier preview, shut down on 2025-12-09.                        |
| `"gemini-2.0-flash-exp"`                                    | Experimental preview, retired Dec 2024.                          |

The defaults change as Google promotes native audio to GA.

## Voices

`Puck`, `Charon`, `Kore`, `Fenrir`, `Aoede` — Gemini's built-in `PrebuiltVoiceConfig` set. Pass any one as `voice`.

## When to use Gemini Live vs alternatives

| Use Gemini Live when…                                | Use [OpenAI Realtime](/typescript-sdk/providers/openai-realtime) when…             | Use [Pipeline mode](/typescript-sdk/agents) when…                                              |
| ---------------------------------------------------- | ---------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------- |
| You want native-audio Gemini voices and 1M+ context. | You need the broadest tool-calling ecosystem and `gpt-realtime-2` reasoning tiers. | You need provider-by-provider control (e.g. `DeepgramSTT` + `AnthropicLLM` + `ElevenLabsTTS`). |

## Notes

* Barge-in is implicit: Gemini Live runs server-side VAD and interrupts on user speech. `cancelResponse()` is a no-op for compatibility.
* The adapter resamples nothing — pass PCM16 mono at `inputSampleRate` Hz. Patter's telephony layer resamples 8 kHz mulaw up to 16 kHz before this point.
* `@google/genai` is imported lazily, so default installs of `getpatter` do not pay the load cost.

## What's Next

<CardGroup cols={2}>
  <Card title="Engines" icon="bolt" href="/typescript-sdk/engines">All engines side by side.</Card>
  <Card title="OpenAI Realtime" icon="bolt" href="/typescript-sdk/providers/openai-realtime">The default engine.</Card>
  <Card title="Agents" icon="user-gear" href="/typescript-sdk/agents">System prompts, tools, first messages.</Card>
  <Card title="Tools" icon="screwdriver-wrench" href="/typescript-sdk/tools">Function calling inside a realtime session.</Card>
</CardGroup>