Gemini 3.8 Flash TTS
Hand Gemini 3.8 Flash TTS a written script and it returns a fully acted voice track, with mood, pacing and 130 languages under your control.
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 Model Built for Direction, Not Presets
The rollout introduced two tiers under one family: an expressive flagship for crafted audio and a lean engine for bulk narration.
- A Shared Launch, Two Distinct WorkloadsGemini 3.8 Flash TTS handles expressive, directed reads, while Flash-Lite TTS keeps per-minute costs down when you generate at scale.
- You Direct the Read Instead of Choosing a PresetStyle prompts per turn, structured speech metadata and inline vocal events together control tone, tempo, feeling and accent.
- Design a Voice From Words, or Replicate With ConsentSketch a voice using plain description, or mirror a real speaker by supplying a reference clip alongside a matching consent file.
How to Prompt Gemini 3.8 Flash TTS for Clean Takes
Four habits that keep your transcript readable and let the performance metadata do the acting.
What Gemini 3.8 Flash TTS Can Actually Do
Performance control, voice design, dialogue staging and 130-language reach — the full toolkit inside the flagship Gemini TTS model.
Line-by-Line Performance Control
Per-turn styling plus inline laughs, sighs, coughs, breaths and pauses feels like coaching a performer rather than picking a stock voice.
Voice Design From Plain Description
Prompts can specify age, personality, accent, vocal texture and role, with 2,000+ ready-made voices available through the Voices endpoint.
Replication Guarded by Consent
You need a clean reference clip and a matching consent clip from the same adult speaker, plus SynthID watermarking and C2PA credentials.
Dialogue Built for Two Speakers
Write the exchange once for podcasts, lessons, product walkthroughs or game scenes — no hand-stitching separate lines together.
Steady Voice Across Long Narrations
Google reports consistent identity, timbre, loudness and room tone across multi-minute narration and drawn-out dialogue.
130 Languages With Regional Color
The flagship supports 130 languages versus Flash-Lite's 101, including regional accents, minority dialects and IPA overrides.
Gemini 3.8 Flash TTS: Questions People Ask Most
Quick answers about Gemini 3.8 Flash TTS costs, picking between tiers, benchmark scores and safety rules.
What does Gemini 3.8 Flash TTS charge per audio minute?
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?
Choose the flagship for acting nuance and long-form pieces; choose Flash-Lite TTS for high volume 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 lowers audio output pricing from $20 to $6 per million tokens.
Can I clone a voice, and what rules apply?
Replication requires a reference clip and a matching consent recording captured from the same adult speaker.
Why does the model read my stage directions aloud?
Your input is treated as a verbatim transcript — shift any lasting directions into the speech metadata fields.
Point Gemini 3.8 Flash TTS at Your Next Script
Try both tiers in the Gemini API or Google AI Studio — moving between Gemini 3.8 Flash TTS and Flash-Lite TTS takes nothing more than swapping a model ID. Weigh batch against priority inference before committing a budget.