Gemini 3.8 Flash TTS
Type a script and Gemini 3.8 Flash TTS performs it your way — shape emotion, stage two speakers and output 130 languages in one API call.
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: Two Tiers Built for Different Audio Jobs
Launched in late September 2026, Google's Gemini TTS family now pairs an expressive flagship with a low-cost engine built for bulk narration.
- A Single Release, Two Very Different JobsThe flagship Gemini 3.8 Flash TTS handles nuanced performance, while Flash-Lite TTS keeps per-minute costs low for high-volume speech.
- You Direct the Performance Instead of Choosing a PresetPer-turn style notes, structured speech metadata and inline vocal tags decide tone, tempo, feeling and regional accent.
- Invent a Voice or Replicate One With ConsentDescribe the voice you want in plain words, or clone a real speaker using a reference clip alongside a matching consent file.
How to Prompt Gemini 3.8 Flash TTS for Clean Output
Four habits that keep your script readable and let the delivery metadata do the acting.
Inside Gemini 3.8 Flash TTS: Every Capability Explained
From fine-grained performance control to 130-language coverage, here is what this flagship Gemini TTS model really delivers.
Granular Control Over Delivery
Per-turn styling plus inline laughs, sighs, coughs, breaths and pauses bring you closer to coaching a voice actor than picking a preset.
Design Voices With Plain English
Describe age, personality, accent, vocal texture and role in a prompt, drawing on 2,000+ production voices through the Voices endpoint.
Voice Cloning Behind a Consent Gate
You need a clean reference clip and a matching consent clip from the same adult speaker, plus SynthID watermarking and C2PA credentials.
Built for Two-Person Dialogue
Write the exchange once for podcasts, lessons, product demos or game scenes — no hand-stitching separate takes together.
Steady Voice Identity Over Long Passages
Google reports consistent identity, timbre, loudness and room tone across multi-minute narration and long conversations.
130 Languages, Regional Accents Included
Flash TTS speaks 130 languages versus Flash-Lite's 101, adding regional accents, minority dialects and IPA pronunciation overrides.
Gemini 3.8 Flash TTS: Questions People Ask Most
Quick answers about cost, which tier to pick, benchmark scores and the safety rules around Gemini 3.8 Flash TTS.
What does Gemini 3.8 Flash TTS charge per audio minute?
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 tier should I pick — Flash TTS or Flash-Lite TTS?
Pick Flash TTS when acting nuance and long-form audio matter; choose Flash-Lite TTS for bulk jobs where latency is critical.
How does it score against rival voice models?
Google cites a 71.4 score on Hume's Voice Design Benchmark, while 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 safeguards are in place?
Cloning requires a reference clip together with a matching consent recording from the same adult speaker.
Why is the model reading my stage directions aloud?
Everything you type is spoken as written, so shift lasting directions into the speech metadata fields.
Run Your Own Scripts Through Gemini 3.8 Flash TTS
Try both tiers inside the Gemini API or Google AI Studio — moving between Gemini 3.8 Flash TTS and Flash-Lite TTS takes nothing more than a model ID swap. Weigh batch against priority inference before you lock in a production budget.