Gemini 3.8 Flash TTS
A text-to-speech model you can direct line by line. Gemini 3.8 Flash TTS renders multi-speaker scripts, sustained emotion and 130 languages in your browser.
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.
Veo3.1
Create Stunning Videos with Veo3.1
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
Gemini 3.8 Flash TTS: A Voice Engine Built for Direction
Google's newest Gemini TTS release ships in two forms — an expressive model for crafted audio and a leaner one tuned for bulk throughput.
- Two Models, Two Very Different JobsThe flagship handles expressive, directed audio, while its lighter sibling keeps the cost per minute low when you need thousands of clips.
- You Direct the Read, You Don't Just Pick a VoiceStyle cues set per turn, structured speech fields and inline vocal tags together control tone, tempo, feeling and accent.
- Invent a Voice, or Clone One With PermissionDescribe the voice you want in plain words, or mirror a real person using a clean sample plus a matching consent recording.
How to Get Clean Results From Gemini 3.8 Flash TTS
Four habits that keep your script readable and leave the acting direction exactly where it belongs.
What Gemini 3.8 Flash TTS Can Actually Do
Direction tools, language reach and safety layers — a closer look at the real strengths of the flagship Gemini TTS model.
Line-by-Line Acting Control
Per-turn style settings plus inline laughs, sighs, coughs, breaths and pauses make it feel like coaching a performer rather than loading a preset.
Describe a Voice, Get That Voice
Prompts can specify age range, personality, accent, vocal texture and role, with 2,000+ ready-made voices available through the Voices endpoint.
Cloning That Requires Permission
You need a clean sample plus a consent recording from the same adult speaker, with SynthID watermarking and C2PA credentials attached to the output.
Conversations for Two Voices
Write both sides of a podcast, lesson, product demo or game scene and skip the manual splicing of separate takes.
Steady Voice Across Long Recordings
Google reports consistent identity, timbre, loudness and room tone through multi-minute narration and extended back-and-forth dialogue.
130 Languages, Regional Accents Included
The flagship speaks 130 languages where the lighter model covers 101, adding regional accents, minority dialects and IPA pronunciation overrides.
Questions People Ask About Gemini 3.8 Flash TTS
Quick answers on cost, which model to pick, how it scores and what safety rules apply.
What does Gemini 3.8 Flash TTS charge per minute of audio?
Roughly 1.35 cents for every audio minute, based on launch pricing of $0.50 per million input tokens and $9 per million output tokens.
Which model should I pick — Flash TTS or Flash-Lite TTS?
Reach for Flash TTS when acting nuance and long narration matter; reach for Flash-Lite TTS when you need volume and fast turnaround.
How does it score against rival voice models?
Google cites a 71.4 result 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 down to $6 per million tokens.
Can I clone a voice, and what rules apply?
Yes — but you must supply a reference clip plus a matching consent recording from that same adult speaker.
Why is the model reading my stage directions aloud?
Because the input is treated as a verbatim transcript — move long-lasting directions into the speech metadata fields instead.
Point Gemini 3.8 Flash TTS at Your Next Script
Try both models in Google AI Studio or the Gemini API — moving between Gemini 3.8 Flash TTS and Flash-Lite TTS is just a different model identifier. Weigh batch against priority inference before you lock in a production budget.