Gemini 3.8 Flash TTS
Speech and audio
gemini-3.8-flash-tts
$0.50 in, $9 out per 1M tokens
Gemini 3.8 Live
Native-audio model for real-time voice and video agents via the Live API (WebSocket, bidirectional streaming).
Model idgemini-3.8-live
Price$0.75 in, $4.50 out per 1M tokens
Checked29 September 2026
Where it stands
25newer speech and audio models since its release
- NVIDIA Nemotron 3.5 Transcribe (30B-A4B)28 Oct 2026
- Hy-SimulMT-30B-A3B22 Oct 2026
- Eleven Realtime v1 Max / Mini20 Oct 2026
- Voxtral Mini Transcribe 3 (+ Mini Transcribe Realtime 3)20 Oct 2026
- Voxtral Small Transcribe 320 Oct 2026
The 5 newest are listed. All speech and audio models
- Before it from Google
- Gemini 3.5 Transcribe (and Transcribe Live)26 Aug 2026
- After it from Google
- Gemini 3.8 Flash-Lite TTS22 Sep 2026
- Weights
- Closed weights; access is hosted only.
How to call it
3 ways to use Gemini 3.8 Live, with the model id each provider expects.
| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| Gemini Live API (WebSocket) | gemini-3.8-live |
wss://generativelanguage.googleapis.com/ws/google.ai.generativelanguage.v1beta.GenerativeService.BidiGenerateContent |
ai.google.dev |
| Gemini Live API (WebSocket) | gemini-3.8-live-extended-thinking |
ai.google.dev | |
| Web app | gemini.google.com |
Pricing
| Input | $0.75 per 1M tokens |
|---|---|
| Output | $4.50 per 1M tokens |
| Audio input | $3 per 1M tokens |
| Audio output | $12 per 1M tokens |
As published: “per 1M tokens (text in $0.75, text out $4.50; audio in $3.00 = ~$0.005/min, audio out $12.00 = ~$0.018/min)”.
Source: ai.google.dev, checked 29 September 2026.
Specs
- Input
- Text, images, audio and video
- Output
- Text and audio
- Context window
- 131,072 tokens
- Max output
- 65,536 tokens
- Open weights
- No
- Licence
- Proprietary
- Released
- 15 September 2026
- Status
- Current
- Type
- Speech and audio
What stands out
What its maker marketed at launch, and what people found later, each with its source.
Real-time multilingual voice agents
Low-latency speech-to-speech with near-real-time visual grounding; 97 languages with mid-conversation switching.
Asynchronous tool use while talking
Keeps the conversation going while tools run in the background, narrating progress (‘Let me check that...’).
Extended Thinking variant tops S2S quality
gemini-3.8-live-extended-thinking ranked #1 on Artificial Analysis Speech-to-Speech Quality Index (82.6) and 97.7% Big Bench Audio.
Notes
Default Live API model; thinking_level not supported on gemini-3.8-live (use gemini-3.8-live-extended-thinking for deeper reasoning; pricing page lists it at the same rates as gemini-3.8-live, checked 2026-09-29). Previous: gemini-3.1-flash-live-preview, gemini-2.5-flash-native-audio-preview-12-2025. WebSocket endpoint is the standard Live API URL, not re-read today.
from google import genai
client = genai.Client()
async with client.aio.live.connect(model="gemini-3.8-live",
config={"response_modalities": ["AUDIO"]}) as session:
await session.send_client_content(turns={"parts": [{"text": "Hi!"}]})
Sources: model page, pricing, launch blog.