Gemini 3.8 Flash TTS
Gemini 3.8 Flash TTS turns your script into directed narration — shape emotion and pacing per line, then export audio in 130 languages right 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.
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.
How Gemini 3.8 Flash TTS Reshapes the Way Teams Build Voice
Launched on September 23, 2026, Google's lineup pairs a creativity-first model with a lean, high-volume tier for bulk narration.
- A Single Release, Two Distinct WorkloadsThe flagship handles nuanced acting, while Flash-Lite TTS serves cost-sensitive, high-volume speech jobs.
- Direction Instead of Preset HuntingPer-turn style notes, structured speech metadata and inline vocal cues govern tone, tempo, mood and accent.
- Voice Design Plus Consented CloningDescribe a timbre in plain words, or replicate a real speaker using a reference clip paired with a matching consent recording.
Getting Clean Results From Gemini 3.8 Flash TTS
Four habits that keep your transcript verbatim while metadata carries the acting notes.
Inside Gemini 3.8 Flash TTS: What It Can Do
Acting notes, voice design, consented cloning and wide language coverage — the full capability set of the flagship model, explained.
Turn-by-Turn Performance Control
Style notes per turn plus inline laughs, sighs, coughs, breaths and pauses — closer to coaching an actor than selecting a preset.
Describe a Voice in Plain Words
Prompts can set age, personality, accent, vocal texture and role, backed by 2,000+ ready voices through the Voices endpoint.
Cloning Behind a Consent Gate
Needs a clean reference recording plus a matching consent clip from the same adult, with SynthID watermarking and C2PA credentials.
Dialogue Built for Two Voices
Scripts drive podcasts, teaching exchanges, product walkthroughs and game scenes without stitching lines together by hand.
Consistent Tone Across Long Recordings
Google documents steady identity, timbre, loudness and room tone through multi-minute narration and extended exchanges.
Broad Language and Accent Coverage
Reaches 130 languages versus 101 on Flash-Lite, including regional accents, minority dialects and IPA pronunciation overrides.
Gemini 3.8 Flash TTS: Questions People Ask Most
Quick answers on cost, model selection, benchmark standing and the safeguards around voice cloning.
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.
When should I pick Flash-Lite TTS instead?
Choose the flagship for acting nuance and long narration; pick Flash-Lite for high-volume output and lower latency.
How does it score against rival voice models?
Google cites 71.4 on Hume's Voice Design Benchmark, and Voice Arena lists 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?
Cloning requires a reference clip plus a matching consent recording from the same adult speaker.
Why is the model speaking my stage directions?
Input is treated as a literal transcript, so move any lasting directions into the speech metadata.
Hear Your Own Script in a Directed Voice
Try the flagship and its lighter sibling inside the Gemini API or AI Studio — swapping between Gemini 3.8 Flash TTS and Flash-Lite TTS takes nothing more than a model identifier. Benchmark batch against priority inference before you lock in a production budget.