# Gemini (/en/ai/platform/models/asr/gemini)

> For AI agents: see the complete documentation index at [llms.txt](/llms.txt).

> Documentation: Conversational AI.
> Documentation version: Preview.
> This document describes only this version. [Version index](/llms/doc-versions-convoai-guides-v2.txt).


Google Gemini provides real-time streaming transcription. Use it as the ASR model in a cascading pipeline with any supported LLM and TTS vendor.

## Sample configuration

The following example shows how to configure Gemini as the agent's ASR when you create or update an agent. For a complete example, see [Create an agent and start a session](/en/ai/platform/get-started/start-stop-agent#create-an-agent).

Gemini supports BYOK only. It isn't available in managed mode. Store your Gemini API key in a secret set, and refer to it from the agent. For details, see [Use your own provider keys](/en/ai/platform/build/use-your-own-keys).

**Python SDK**

```python
from agora_agent import Agent, GeminiSTT, secret_ref

# client is your configured Agora client
agent = (
    Agent(client=client)
    .with_stt(
        GeminiSTT(
            api_key=secret_ref("support_prod", "gemini"),
            model="gemini-3.5-transcribe-live",
            language="en-US",
            sample_rate=16000,
            word_timestamp=True,
        )
    )
    .with_llm(...)  # configure your LLM vendor
    .with_tts(...)  # configure your TTS vendor
)
```

**TypeScript SDK**

```ts
import { Agent, GeminiSTT, secretRef } from 'agora-agents';

// client is your configured Agora client
const agent = new Agent({ client })
  .withStt(
    new GeminiSTT({
      apiKey: secretRef('support_prod', 'gemini'),
      model: 'gemini-3.5-transcribe-live',
      language: 'en-US',
      sampleRate: 16000,
      wordTimestamp: true,
    }),
  )
  .withLlm(/* configure your LLM vendor */)
  .withTts(/* configure your TTS vendor */);
```

**Go SDK**

```go
wordTimestamp := true

// client is your configured Agora client
agent := agentkit.NewAgent(client).
	WithStt(vendors.NewGeminiSTT(vendors.GeminiSTTOptions{
		APIKey:        agentkit.SecretRef("support_prod", "gemini"),
		Model:         "gemini-3.5-transcribe-live",
		Language:      "en-US",
		SampleRate:    16000,
		WordTimestamp: &wordTimestamp,
	})).
	WithLlm( /* configure your LLM vendor */ ).
	WithTts( /* configure your TTS vendor */ )
```

**REST API**

Set `credential.mode` to `byok` and `credential.fields.api_key` to a reference to your Gemini API key in a secret set. In the following example, the key is stored as `gemini` in the `support_prod` set:

```json
"asr": {
  "credential": {
    "mode": "byok",
    "fields": {
      "api_key": "$secrets.support_prod.gemini"
    }
  },
  "vendor": "gemini",
  "model": "gemini-3.5-transcribe-live",
  "language": "en-US",
  "params": {
    "sample_rate": 16000,
    "word_timestamp": true
  }
}
```

## Key parameters

The `asr` block takes the following fields. In the SDKs, `GeminiSTT` sets them from its options, and passes any other Gemini parameters from its additional parameters option to `params`.

**asr required**

**`vendor` (string) required**

Set to `gemini`.

**`credential` (object) required**

How the agent authenticates with Gemini. Set `mode` to `byok` and `fields.api_key` to a `$secrets.<set>.<key>` reference to your Google Gemini API key. You can generate an API key in [Google AI Studio](https://aistudio.google.com/apikey).

**`model` (string) required**

The Gemini transcription model identifier. Set to `gemini-3.5-transcribe-live` to use Gemini 3.5 Transcribe Live.

**`language` (string) required**

The BCP-47 language tag identifying the primary language used for agent interaction, for example, `en-US`.

**`params` (object) optional**

**`sample_rate` (integer) optional**

The audio sample rate in Hz. For example, `16000`.

**`word_timestamp` (boolean) optional**

Whether to include word-level timestamps in the transcription results.

> **Caution**
>
> The parameters listed on this page are validated for use with the Conversational AI Platform. Required parameters must be provided as documented. Any additional parameters in `params` are passed through directly to Gemini without validation. For a full list of supported options, refer to the [Google Gemini API documentation](https://ai.google.dev/api/live).