Gemini 3.8 Flash TTS
Gemini 3.8 Flash TTS reads your script the way you intend — describe a voice, mark the emotions and render natural speech in 130 languages, no setup.
Support
Pro AI Tools
Explore elite tools including the Suno AI Music Generator.
MiniMax H3
MiniMax H3 AI Video Generator
Seedance 2.5
The Future of AI Video Is Here.
Seedance 2.0
The Future of AI Video Is Here.
FLUX 3 Video Generator
Kling 3.0
Next-Gen AI Video Generator
Grok Video Generator
Create Videos from Text or Images with AI
MiniMax H3 video generator
MiniMax H3 AI Video Generator
Seedance 2.0
The Future of AI Video Is Here.
Gemini 3.8 Flash TTS and the Shift in How Audio Gets Made
Announced on September 23, 2026, the Gemini TTS family arrives in two forms: a creative flagship for expressive work and a leaner tier built for bulk narration.
- Two Models, Two Very Different JobsThe flagship handles nuanced performance work, while Flash-Lite TTS keeps spending low when you need thousands of minutes.
- You Direct the Performance, Not Just the VoicePer-turn style notes, structured speech metadata and inline vocal events shape tone, tempo, feeling and accent.
- Design a Voice From Words, or Clone With ConsentWrite a description to invent a voice, or reproduce a real one using a sample plus a matching consent recording.
Four Rules for Getting Clean Audio Out of Gemini 3.8 Flash TTS
Follow these habits and your transcript stays untouched while the delivery notes do the acting.
What Gemini 3.8 Flash TTS Can Actually Do
From line-by-line acting notes to 130-language coverage, these are the strengths that set the flagship Gemini TTS model apart.
Line-Level Performance Control
Style tags on each turn plus inline laughs, sighs, coughs, breaths and pauses — closer to coaching an actor than picking a preset.
Invent Voices With Plain Words
Describe age range, personality, accent, vocal texture and role in a prompt, with 2,000+ ready-made voices also reachable through the Voices endpoint.
Replication That Requires Permission
You need a clean reference recording plus a matching consent recording from the same adult speaker, backed by SynthID watermarking and C2PA credentials.
Built-In Two-Person Scenes
Podcasts, lessons, product demos and game cutscenes come together in a single pass, with no manual line stitching.
Steady Voice Across Long Recordings
Google documents consistent voice identity, timbre, volume and room tone across multi-minute narration and extended dialogue.
130 Languages With Regional Color
The flagship covers 130 languages against Flash-Lite's 101, including regional accents, minority dialects and IPA pronunciation overrides.
Answers to Common Gemini 3.8 Flash TTS Questions
Quick replies about cost, model selection, benchmark scores and the safeguards behind Gemini 3.8 Flash TTS.
What does Gemini 3.8 Flash TTS charge per minute of audio?
Roughly 1.35 cents per audio minute, based on launch pricing of $0.50 per million input tokens and $9 per million output tokens.
When should I pick Flash-Lite TTS instead?
Reach for the flagship when acting nuance and long-form audio matter; choose Flash-Lite TTS for bulk output and low latency.
How does it score against rival voice models?
Google cites 71.4 on Hume's Voice Design Benchmark, and Voice Arena ranks it second with 1,260 Elo.
What changed from the Gemini 3.1 Flash TTS Preview?
Flash-Lite TTS takes over from the 3.1 preview and drops audio output pricing from $20 to $6 per million tokens.
Can I clone a voice, and what rules apply?
Yes — but replication requires a reference clip plus a matching consent recording from the same adult speaker.
Why does the model speak my stage directions out loud?
Because the input is read as a verbatim transcript; move any sustained directions into the speech metadata instead.
Run Your First Gemini 3.8 Flash TTS Session Today
Both tiers live inside the Gemini API and Google AI Studio, and moving between Gemini 3.8 Flash TTS and Flash-Lite TTS means changing a single model identifier. Test batch and priority inference side by side before you lock in a production budget.