Gemini 3.8 Flash TTS

Type a script and hear it acted: shape emotion line by line, cast two speakers and render 130 languages with Gemini 3.8 Flash TTS.

Gemini 3.8 Flash TTS
Steer every line's emotion on the flagship tier, or switch to Flash-Lite TTS for high-volume, low-cost speech
AI Video Prompt Generator

Support

Pro AI Tools

Explore elite tools including the Suno AI Music Generator.

placeholder hero

How Gemini 3.8 Flash TTS Turns a Script into a Performance

Launched September 23, 2026, Google's new tier pairs a creative flagship with a budget-friendly sibling built for mass audio production.

  • Two Tiers, Two Very Different Jobs
    Gemini 3.8 Flash TTS handles nuanced acting, while Flash-Lite TTS keeps bulk narration fast and inexpensive.
  • Steer Delivery Instead of Choosing a Preset
    Style notes per turn, structured speech metadata and inline vocal events control emotion, tempo, accent and emphasis.
  • Invent Voices or Replicate with Permission
    Describe a voice in plain language, or reproduce a real speaker using a reference clip plus a matching consent recording.

How to Prompt Gemini 3.8 Flash TTS for Clean Results

Four habits that keep your transcript word-for-word while the performance metadata handles the acting.

Inside Gemini 3.8 Flash TTS: What It Can Do

From line-by-line direction to 130-language output, here is what this flagship voice model actually delivers.

Line-Level Performance Control

Style per turn plus inline laughs, sighs, coughs, breaths and pauses — closer to coaching a voice actor than picking a preset.

Voices Described in Plain English

Prompts capture age, personality, accent, texture and role, drawing on 2,000+ production voices from the Voices endpoint.

Replication Guarded by Consent

A clean reference recording plus a matching consent clip from the same adult speaker, with SynthID watermarking and C2PA credentials.

Built-In Two-Person Scenes

Scripts carry the whole conversation for podcasts, lessons, product demos and game scenes — no manual line stitching.

Steady Voice Across Long Recordings

Google documents consistent identity, timbre, volume and room tone across multi-minute narration and extended dialogue.

130 Languages with Regional Accents

Flash TTS covers 130 languages versus Flash-Lite's 101, including regional accents, minority dialects and IPA pronunciation overrides.

FAQ

Gemini 3.8 Flash TTS: Your Questions Answered

Quick answers on pricing, picking the right tier, benchmark scores and the safeguards around voice replication.

1

What does Gemini 3.8 Flash TTS charge per audio minute?

Roughly 1.35 cents per minute at launch pricing of $0.50 per million input tokens and $9 per million output tokens.

2

Which tier fits my project — Flash or Flash-Lite?

Choose Flash TTS for acting nuance and long-form audio; reach for Flash-Lite TTS when you need bulk output and low latency.

3

How does it score against rival voice models?

Google reports 71.4 on Hume's Voice Design Benchmark, while Voice Arena ranks it second with 1,260 Elo.

4

What changed from the Gemini 3.1 Flash TTS Preview?

Flash-Lite TTS supersedes the 3.1 preview and drops audio output pricing from $20 to $6 per million tokens.

5

Can I replicate a real voice, and what rules apply?

Replication requires a reference clip plus a matching consent recording from the same adult speaker.

6

Why is the model reading my stage directions aloud?

Input is treated as a verbatim transcript, so move sustained directions into speech metadata instead.

Hear Your Own Script Performed by Gemini 3.8 Flash TTS

Try both tiers inside the Gemini API or Google AI Studio — moving between the flagship and Flash-Lite TTS takes nothing more than a model ID swap. Weigh batch against priority inference before you lock in a production budget.