> For the complete documentation index, see [llms.txt](https://docs.aimlapi.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.aimlapi.com/api-references/realtime-models/google/gemini-3.8-live.md).
# Gemini 3.8 Live
{% columns %}
{% column width="66.66666666666666%" %}
{% hint style="info" %}
This documentation is valid for the following list of our models:
* `google/gemini-3.8-live`
* `gemini-3.8-live`
{% endhint %}
{% endcolumn %}
{% column width="33.33333333333334%" %} Try in Playground
{% endcolumn %}
{% endcolumns %}
Google's Live API model for real-time voice and video conversations: it takes streamed speech, text and camera or screen frames, and answers with speech or text, with function calling. Sessions speak Google's Gemini Live protocol, so the official Google GenAI SDKs work with only the base URL changed.
## Setup your API Key
If you don’t have an API key for the AI/ML API yet, feel free to use our [Quickstart guide](https://docs.aimlapi.com/quickstart/setting-up).
## API Schema
The model is served over a WebSocket in the Gemini Live protocol. Client messages, billing, limits and errors are described in [Realtime Sessions](/capabilities/realtime-sessions.md#gemini-live).
| | |
| ------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Connection URL (API key) | `wss://api.aimlapi.com/ws/google.ai.generativelanguage.v1beta.GenerativeService.BidiGenerateContent` (`v1alpha` also works), with the key in `x-goog-api-key` or `Authorization: Bearer` |
| Connection URL (client secret) | `wss://api.aimlapi.com/ws/google.ai.generativelanguage.v1alpha.GenerativeService.BidiGenerateContentConstrained` (`v1beta` also works), with the secret as `access_token` or in `Authorization: Token` ([client secrets](/capabilities/realtime-sessions.md#browsers-client-secrets)) |
| SDK base URL | `https://api.aimlapi.com` |
| JavaScript SDK | `@google/genai` sends a plain API key in the URL, which is refused (`400 credential_in_query`): pass a client secret as its API key with `apiVersion: "v1alpha"`, as in the example below |
Session options (`setup`, the first message, sent once within 10 seconds of connecting; `model` is `gemini-3.8-live`, `google/gemini-3.8-live`, `models/gemini-3.8-live` or `models/google/gemini-3.8-live`):
| Option | Values |
| --------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------- |
| `generationConfig.responseModalities` | `AUDIO` (default) and/or `TEXT` |
| `generationConfig.maxOutputTokens` | Kept between 1,024 and 4,096 (default 4,096); thinking counts inside it |
| `generationConfig.temperature`, `topP`, `topK`, `presencePenalty`, `frequencyPenalty`, `seed` | As in the Gemini API; `candidateCount` 1 only |
| `generationConfig.speechConfig` | `voiceConfig.prebuiltVoiceConfig.voiceName` (a prebuilt voice such as `Puck` or `Kore`), `languageCode` |
| `generationConfig.mediaResolution` | `MEDIA_RESOLUTION_LOW`, `_MEDIUM`, `_HIGH` |
| `systemInstruction` | Up to 8 text parts of 16,384 characters |
| `tools` | `functionDeclarations` only, up to 32 |
| `realtimeInputConfig` | `automaticActivityDetection`, `activityHandling`, `turnCoverage` |
| `outputAudioTranscription` | Transcript of the model's speech |
| `historyConfig.initialHistoryInClientContent` | `true` or `false` |
## Code Example
{% tabs %}
{% tab title="Python" %}
{% code overflow="wrap" %}
```python
# pip install google-genai
import asyncio
from google import genai
from google.genai import types
client = genai.Client(
# Insert your AI/ML API key instead of :
api_key="",
http_options=types.HttpOptions(base_url="https://api.aimlapi.com"),
)
async def main():
async with client.aio.live.connect(
model="gemini-3.8-live",
config=types.LiveConnectConfig(response_modalities=["AUDIO"]),
) as session:
await session.send_client_content(
turns=types.Content(role="user", parts=[types.Part(text="Say hi in two words.")]),
turn_complete=True,
)
audio = bytearray()
async for message in session.receive():
if message.data:
audio += message.data # raw PCM16 audio from the model
if message.usage_metadata:
print("Usage:", message.usage_metadata)
if message.server_content and message.server_content.turn_complete:
break
print(f"Received {len(audio)} bytes of audio")
asyncio.run(main())
```
{% endcode %}
{% endtab %}
{% tab title="JavaScript" %}
{% code overflow="wrap" %}
```javascript
// npm i @google/genai
import { GoogleGenAI, Modality } from "@google/genai";
// Insert your AI/ML API key instead of .
// Mint this on your server; a browser receives only the secret.
const response = await fetch("https://api.aimlapi.com/v1/realtime/client_secrets", {
method: "POST",
headers: {
Authorization: "Bearer ",
"Content-Type": "application/json",
},
body: JSON.stringify({ session: { model: "google/gemini-3.8-live" } }),
});
const { value: secret } = await response.json(); // "auth_tokens/aiml_ek_..."
const ai = new GoogleGenAI({
apiKey: secret,
httpOptions: { baseUrl: "https://api.aimlapi.com", apiVersion: "v1alpha" },
});
let done;
const turnComplete = new Promise((resolve) => (done = resolve));
const session = await ai.live.connect({
model: "gemini-3.8-live",
config: { responseModalities: [Modality.AUDIO] },
callbacks: {
onmessage: (message) => {
if (message.usageMetadata) {
console.log("Usage:", message.usageMetadata);
}
if (message.serverContent?.turnComplete) {
done();
}
},
onerror: (error) => console.error("Error:", error?.message ?? error),
onclose: (event) => console.log("Closed", event?.code, event?.reason),
},
});
session.sendClientContent({ turns: "Say hi in two words.", turnComplete: true });
await turnComplete;
session.close();
```
{% endcode %}
{% endtab %}
{% endtabs %}
Response
The example sends one typed turn and collects the spoken answer (raw PCM16 audio) until the turn is complete. The Python version prints the token usage Google reports and the size of the received audio. Values in angle brackets are placeholders.
{% code overflow="wrap" %}
```
Usage:
Received bytes of audio
```
{% endcode %}
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.
Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:
```
GET https://docs.aimlapi.com/api-references/realtime-models/google/gemini-3.8-live.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.