Voice conversation that keeps talking while it reasons in the background, with 30 voices, live video input, tool calling, and adjustable reasoning effort.
GoogleAudio Generation128K contextReleased Sep 15, 2026Proprietary EndpointNewVoice conversation that keeps talking while it reasons in the background, with 30 voices, live video input, tool calling, and adjustable reasoning effort.
Session is configured with session.update events over the socket rather than request parameters. Text and audio tokens bill at separate rates.
Also known as Gemini Live Extended Thinking, Google Gemini 3.8 Live Extended Thinking
gemini-3-8-live-extended-thinking/v1/realtimegemini-3.8-live-extended-thinkinggoogle/gemini-3.8-live-extended-thinkingLive pay-as-you-go rates from the EmpirioLabs catalog. You are billed only for what you use, with no monthly minimum.
Gemini 3.8 Live Extended Thinking holds a live conversation over a WebSocket at wss://api.empiriolabs.ai/v1/realtime?model=gemini-3-8-live-extended-thinking, not over the HTTP endpoints. Connect with the model id gemini-3-8-live-extended-thinking and send your EmpirioLabs API key as an Authorization: Bearer header on the handshake. Audio travels both ways as base64 16-bit PCM. A browser cannot set headers on a WebSocket, so open this connection from your server and relay audio to the browser over your own socket. Get an API key from the EmpirioLabs dashboard.
import asyncio, json, os, websockets
async def main():
async with websockets.connect(
"wss://api.empiriolabs.ai/v1/realtime?model=gemini-3-8-live-extended-thinking",
additional_headers=[
("Authorization", f"Bearer {os.environ['EMPIRIOLABS_API_KEY']}"),
],
max_size=None,
) as ws:
print(json.loads(await ws.recv())["type"]) # session.created
await ws.send(json.dumps({
"type": "conversation.item.create",
"item": {
"type": "message",
"role": "user",
"content": [{"type": "input_text", "text": "Say hello."}],
},
}))
await ws.send(json.dumps({"type": "response.create"}))
async for raw in ws:
event = json.loads(raw)
if event["type"] == "response.audio.delta":
... # base64 audio chunk, append to your playback buffer
elif event["type"] == "response.done":
break
asyncio.run(main())Request parameters supported by the Gemini 3.8 Live Extended Thinking API on EmpirioLabs. Defaults apply when a field is omitted.
| Parameter | Type | Default | Range / values | Description |
|---|---|---|---|---|
| voice | enum | Puck | Zephyr, Puck, Charon, Kore, Fenrir, Leda, Orus, Aoede, Callir... | Speaking voice for the session. Set it with session.update before the conversation starts; it cannot change afterwards. |
| instructions | string | - | - | System guidance for how the model behaves and speaks. Set it with session.update before the conversation starts. |
| reasoning_effort | enum | medium | low, medium, high | How much the model reasons in the background while it talks. Higher effort uses more output tokens. Set it before the conversation starts. |
| temperature | number | - | 0 to 2 | Sampling temperature from 0 to 2. Lower values make replies more consistent. Set it before the conversation starts. |
| input_audio_format | enum | pcm16 | pcm16, pcm24 | Encoding of the audio you append to the input buffer: pcm16 is base64 16-bit PCM at 16 kHz, and pcm24 is the same at 24 kHz. |
| output_audio_format | enum | pcm24 | pcm24 | Encoding of the audio the model streams back: 16-bit PCM at 24 kHz. |
| turn_detection | string | {"type":"server_vad"} | - | Server-side voice activity detection. Decides when you have stopped speaking and the model should reply. It is on by default; set it to null to end each turn... |
Full-duplex voice over a WebSocket at wss://api.empiriolabs.ai/v1/realtime?model=gemini-3-8-live-extended-thinking, authenticated with the ordinary Authorization Bearer header. Configure the session with session.update before you send the first audio: voice, instructions, turn detection and tools. These settings are fixed once the conversation starts.
Audio and text tokens are priced separately in both directions, video frames bill as input tokens, and reasoning tokens bill as output tokens. Each completed turn is billed on its own from the usage the model reports, including a reply you interrupt.
On EmpirioLabs, Gemini 3.8 Live Extended Thinking is billed pay as you go: Input: audio $7.80 per 1M audio input tokens; Input $2.60 per 1M prompt tokens; Output $11.70 per 1M generated tokens; Output: audio $31.20 per 1M generated audio tokens. The live rate card on this page always matches what the API charges.
Gemini 3.8 Live Extended Thinking supports a 128K-token context window with up to 65,536 output tokens per response.
Gemini 3.8 Live Extended Thinking is served through WEBSOCKET /v1/realtime on api.empiriolabs.ai with standard bearer-token authentication.
Open the EmpirioLabs playground and press Start session to try it in your browser. Gemini 3.8 Live Extended Thinking runs over a WebSocket rather than a request and response, so to build with it start from the realtime voice quickstart. Connect from your server with your EmpirioLabs API key and the model id gemini-3-8-live-extended-thinking, then stream audio in both directions.
Create an EmpirioLabs account, then generate a key under API Keys in the dashboard. Billing is pay-as-you-go credits, so you only pay for the requests you make.
Check out our pricing or reach out if you want your own model deployed on our stack.
