When was Gemini 3.8 Flash TTS released?

Google released Gemini 3.8 Flash TTS on 22 Sep 2026. It is available through the Opper gateway.

Does Gemini 3.8 Flash TTS support zero data retention?

With abuse monitoring, yes. On Google Cloud through the Opper gateway, prompts and outputs are not used for training and are kept only for abuse monitoring.

Where is Gemini 3.8 Flash TTS hosted?

Gemini 3.8 Flash TTS runs on both EU and US hosting routes through the Opper gateway. Pick the route that matches your residency requirement.

Is Gemini 3.8 Flash TTS trained on prompts and outputs?

No. Every hosting route for Gemini 3.8 Flash TTS is configured so customer prompts and outputs are not used to train models by default.

Is a GDPR DPA available for Gemini 3.8 Flash TTS?

Yes. A GDPR Data Processing Agreement is available on at least one route serving Gemini 3.8 Flash TTS. Contact hello@opper.ai to receive it.

Gemini 3.8 Flash TTS

by Google

Announcement · All Google releases

Gemini 3.8 Flash TTS is Google's main text-to-speech model, released September 22, 2026. Google describes it as engineered for studio-grade voice fidelity, expressive acting and long-form stability, and names it, with 3.8 Flash-Lite TTS, as the replacement for the Gemini 2.5 and 3.1 TTS models. It turns text into speech in 30 prebuilt voices, detects the language automatically across more than 100 languages, and follows style directions in the prompt, such as tone, pace or accent. It takes up to 8,192 input tokens per request. It suits narration, audiobooks, podcasts and voice agents where expressiveness matters; 3.8 Flash-Lite TTS is the cheaper choice for high-volume speech.

Call Gemini 3.8 Flash TTS on Opper through POST /v3/audio/speech. Sign up without a credit card. Get started

Get your API key Try in chat Compare

Key info

Input

Output

Features

Context window

Max output

16K

Text input price

$0.50 /1M

Audio output price

$9.00 /1M

Released

22 Sep 2026

EU residency available on Google Cloud
US residency available on Google Cloud
Zero data retention with abuse monitoring
No training by default
GDPR DPA available

Available routes

Gemini 3.8 Flash TTS runs on 2 different routes through the Opper gateway. Compare residency, zero data retention and training posture at a glance, with full data-handling detail per route below. In the EU it is served by Google Cloud. See every Gemini model hosted in the EU.

Provider	Region	Zero data retention	Training	Input	Output	Cache read
Google Cloud	US		No	$0.50	$9.00 audio	Input price
Google Cloud	EU		No	$0.50	$9.00 audio	Input price

Live routes and prices as JSON: api.opper.ai/v3/models?q=gemini%2Fgemini-3.8-flash-tts

Uptime and availability

Gemini 3.8 Flash TTS runs on a single route through the Opper gateway today, so its availability is that provider's availability.

98.04%route uptime, last 30 days

Single route, no failover target within this model.

Name a second model in the same request and the gateway tries it on retriable errors, so a busy hour never has to reach your users. Set up a fallback chain.

Measured over the last 30 days from each provider's official status feed via StatusGator. Refreshed hourly. See uptime for every provider Opper monitors.

Data handling per route

Each route hosting Gemini 3.8 Flash TTS has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

Google Cloud — United States🇺🇸

Zero data retention with abuse monitoring: prompts and outputs are kept for abuse monitoring only, for a window the provider does not state, and are not used for training. No training on customer data. US; SCCs; DPA available.

Zero data retention: With abuse monitoring, window not stated.
Training: No training on customer data.
Logging: Abuse monitoring
Abuse monitoring: On by default, holds flagged content, 55 days, a person can view samples
GDPR DPA: DPA available
Transfer mechanism: SCCs

Google Cloud — EU🇪🇺

Zero data retention with abuse monitoring: nothing is logged or used for training; content flagged by abuse monitoring is held for review. No training on customer data. EU; DPA available.

Zero data retention: With abuse monitoring, flagged content held.
Training: No training on customer data.
Logging: None
Abuse monitoring: On by default, holds flagged content, 90 days, a person can view samples
GDPR DPA: DPA available
Transfer mechanism: Not applicable — data stays in EU

Get started

Call Gemini 3.8 Flash TTS through the Opper gateway with one API key. Text-to-speech models run on POST /v3/audio/speech, which returns the audio in the response. The OpenAI SDK works too, through /v3/compat/audio/speech.

See the Opper audio guide and the Opper multimodal skill.

Gemini 3.8 Flash TTS is a premium model on Opper. Sign up needs no credit card: you get an API key straight away and the free models work in the playground and the API. Add a card to use premium models, pay-as-you-go with no minimum.

Set it up with your agent

Copy this and paste it into a coding agent like Claude Code, Cursor or Codex and it'll wire up Opper for you.

Or call it directly

1curl -s https://api.opper.ai/v3/audio/speech \
2  -H "Authorization: Bearer $OPPER_API_KEY" \
3  -H "Content-Type: application/json" \
4  -d '{
5    "model": "gemini/gemini-3.8-flash-tts",
6    "input": "Hello from Opper.",
7    "voice": "Kore"
8  }' \
9  | jq -r '.audio.b64_json' | base64 --decode > speech.mp3