Audio generation
Available now

Gemini 3.8 Flash TTS

by Google DeepMind

Google's voice for narration and dialogue.
Laughs, sighs and pauses land where you write them.

Gemini 3.8 Flash TTS

Key features

Technical specifications

Up to 2

Two distinct voices in one dialogue generation

10,000 chars

Maximum script length per speech generation

2

Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS

SynthID

Inaudible AI-provenance mark on every clip

Use cases

A long steady band of white light running beneath a row of faint glowing panels

Video narration

Lay a narrator under an AI or live-action cut, then regenerate one line when the edit changes.

A cool blue beam and a warm gold beam meeting in the centre of the frame

Character dialogue

Two-voice scenes for shorts, games and explainers, with each reply timed to the line before it.

Thin sheets of amber light fanning open in depth like leaves

Audiobooks and long-form

Work through a chapter in long passages with one cast voice, and place the breaths and pauses yourself.

A rose wave and a pale blue wave of light crossing as they flow

Podcast intros and segments

A host and a guest in one generation, for cold opens, ad breaks and recap segments.

One white ribbon of light dividing into five soft coloured ribbons side by side

Localized voice-over

Run the same script in another language from the same voice picker, filtered to native voices.

Neat rows of small light points receding, a few glowing gold

High-volume reads

Use Flash-Lite for product reads, read-aloud and drafts, then render the keepers on Flash.

Prompt examples

A warm amber curve of light ending in a burst of sparks

Laugh on cue

I said I'd be on time. <laugh> I meant on time for me.

0:00
0:12
Edit prompt
A smooth pale sphere of light glowing softly in haze

Breath before news

Okay. <breath> We got the grant. All of it.

0:00
0:12
Edit prompt
A thin vertical seam of cold blue light splitting the dark

Pause for effect

The door was already open. <short pause> Someone had been inside.

0:00
0:12
Edit prompt
A dim amber arc drooping downward and fading into smoke

Tired sigh

<sigh> Third train cancelled this week. I'm walking.

0:00
0:12
Edit prompt
Three softly lit white steps rising from left to right

Product walkthrough

Tap the plus icon, pick a template, and your first page is ready.

0:00
0:12
Edit prompt
A blue orb and a gold orb joined by a thin flare of light

Two-voice exchange

Ines: Did the parcel come? Theo: It did. <gasp> It's the wrong colour.

0:00
0:12
Edit prompt

Overview

Gemini 3.8 Flash TTS is Google's text-to-speech model, launched on September 23, 2026 with a faster sibling, Gemini 3.8 Flash-Lite TTS. It reads a script in a voice from Google's voice library, performs the laughs, sighs and pauses you place inline, and voices scenes between two speakers.

What Gemini 3.8 Flash TTS does differently

Gemini 3.8 reads your script as a word-for-word transcript. Sounds go exactly where you put them, written in angle brackets such as <laugh> or <short pause>, and nothing outside them gets performed as an instruction. That makes a take easy to predict and easy to fix: move one tag and generate again. The trade is that tone comes from the voice you cast and the way the line is written, not from a note telling the voice how to feel.

Gemini 3.8 Flash TTS on Morphic

On Morphic, Gemini 3.8 Flash TTS runs in Speech for single-voice scripts of up to 10,000 characters and in Dialogue for two-speaker scenes. Pick it in the Audio model picker, choose voices from Google's library filtered by language and accent, and the audio lands on your Canvas. Gemini 3.8 Flash-Lite TTS uses the same voices at a faster, lower-cost setting. It replaced the retired Gemini 3.1 Flash TTS.

Simple pricing

Get started for free today, with the option to upgrade or cancel anytime.

Basic

$19/ month
billed as $228 per year

2400 monthly credits

1 user only

All models

Workflows

Standard

$24/ month
billed as $288 per year

3625 monthly credits

1 user only

All models

Workflows

Pro

$45/ month
billed as $540 per year

6350 shared monthly credits

1 user

+ up to 4 more at extra cost

All models

Workflows

Max

$170/ month
billed as $2040 per year

24650 shared monthly credits

1 user

+ up to 9 more at extra cost

All models

Workflows

Enterprise

For higher limits

Custom

pricing and billing terms

High-volume credits
Custom seat limits
All models
Workflows
Pricing Gradient

Free

For playing around

$0

forever free

Up to 20 credits
1 user only
Limited models
Workflows

FAQs

What is Gemini 3.8 Flash TTS?
Gemini 3.8 Flash TTS is Google's text-to-speech model, launched on September 23, 2026 alongside a faster sibling, Gemini 3.8 Flash-Lite TTS. It reads a script in a voice from Google's voice library, performs laughs, sighs and pauses you place inline, and voices two-speaker scenes. On Morphic it runs in Speech and Dialogue.
How do I add a laugh, a sigh or a pause?
Write the sound in angle brackets at the point it should happen, such as <laugh>, <sigh>, <gasp>, <breath> or <short pause>. Gemini performs the sound there instead of reading the tag aloud. Keep tags next to the words they belong to, and generate a second take if one lands early.
Can I tell it to say a line cheerfully or slowly?
Not with a written instruction in the script. Gemini 3.8 treats the text as a word-for-word transcript, so a line like 'Say this cheerfully:' can be read out. Shape the delivery with the voice you pick, the punctuation, and inline sound tags. This is the main change if you are moving scripts over from Gemini 3.1 Flash TTS.
How many speakers can one dialogue have?
Two. Switch to Dialogue, give each speaker a voice, and write at least two lines. A whole scene can run to about 8,000 characters of English text across both speakers. For a third character, generate that part separately and place it on your Canvas.
What is the difference between Flash and Flash-Lite?
They share the same voices and the same way of writing a script. Gemini 3.8 Flash TTS gives the fullest acting and is the one to use for audiobooks, character scenes and hard-to-pronounce names. Flash-Lite TTS is faster and costs less per second of audio, which suits read-aloud, drafts and high-volume work.
What languages does Gemini 3.8 Flash TTS speak?
Google lists more than 100 languages for both tiers in its model documentation. In Morphic's voice picker, filter by language to find voices recorded natively in it, then write the script in that language.
Does it replace Gemini 3.1 Flash TTS?
Yes. Gemini 3.1 Flash TTS is retired on Morphic, and requests that named it now run on Gemini 3.8 Flash TTS. The 3.8 models speak the full Google voice library rather than the 30 voices 3.1 offered.
Is the audio watermarked?
Yes. Google marks every clip from its Gemini audio models with SynthID, an inaudible watermark that identifies it as AI-generated (source). It does not change how the voice sounds.
Is Gemini 3.8 Flash TTS free to use on Morphic?
Yes, both Gemini 3.8 Flash TTS and Flash-Lite TTS run on Morphic's free tier. Credits are charged by the length of the audio that comes back, and paid plans add more credits for longer scripts.
How do I use Gemini 3.8 Flash TTS on Morphic?
Open Morphic, switch the prompt bar to Audio and choose Speech or Dialogue. Pick Gemini 3.8 Flash TTS as the model, choose a voice for each speaker, paste your script, and generate. The audio lands on your Canvas next to your video clips.