Gemini 3.8 Flash TTS
Type a script, set the mood for each line, and let Gemini 3.8 Flash TTS render acted speech 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.
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
Two Tiers, One Launch: Inside Gemini 3.8 Flash TTS
Google's September 23, 2026 release splits its speech family in two: an expressive flagship for directed performance and a lean workhorse built for bulk audio.
- A Single Release, Two Very Different JobsGemini 3.8 Flash TTS carries the expressive work, while Flash-Lite TTS keeps per-minute costs low for mass-produced narration.
- Style Commands Instead of Stock PresetsPer-turn instructions, structured speech metadata and inline vocal cues steer emotion, tempo, accent and emphasis.
- Invent a Voice or Replicate One With ConsentDescribe a persona in plain language, or recreate a real speaker from a reference clip paired with a matching consent recording.
How to Prompt Gemini 3.8 Flash TTS for Clean Takes
Four habits that keep your transcript untouched while the performance metadata does the acting.
A Closer Look at Gemini 3.8 Flash TTS Features
From line-by-line performance control to coverage of 130 languages, here is what Google's top voice model actually delivers.
Line-by-Line Performance Control
Per-turn styling plus inline laughs, sighs, coughs, breaths and pauses feels closer to coaching an actor than picking a preset.
Voices Designed From Plain Language
Describe age, personality, accent, vocal texture and role; the Voices endpoint opens more than 2,000 production-ready voices.
Replication That Requires Consent
You supply a clean reference recording plus a matching consent clip from the same adult speaker, with SynthID watermarks and C2PA credentials attached.
Dialogue for Two Speakers, Staged in One Pass
Podcasts, training dialogues, product walkthroughs and game scenes get their conversation from a single script — no manual line stitching.
Consistent Voice Across Long Recordings
Google documents steady identity, timbre, volume and room tone across multi-minute narration and extended back-and-forth dialogue.
130 Languages With Regional Nuance
Flash TTS reaches 130 languages versus 101 on Flash-Lite, with regional accents, minority dialects and IPA overrides for tricky words.
Common Questions About Gemini 3.8 Flash TTS
Quick answers on what this model costs, which tier to pick, how it scores and which safeguards apply.
What does Gemini 3.8 Flash TTS charge per audio minute?
Roughly 1.35 cents per minute, based on launch pricing of $0.50 per million input tokens and $9 per million output tokens.
Flash TTS or Flash-Lite TTS — which one fits my project?
Choose Flash TTS when acting nuance and long-form audio matter; choose Flash-Lite TTS for volume output and snappy latency.
How does it score against rival voice models?
Google cites 71.4 on Hume's Voice Design Benchmark, and Voice Arena puts it in second place 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 replicate a voice, and what protections exist?
Cloning requires a reference clip plus a consent recording from the same adult speaker before any replication is allowed.
Why is the model reading my stage directions aloud?
Everything in the input is treated as transcript, so shift any lasting direction into the speech metadata field.
Run Gemini 3.8 Flash TTS on Your Next Script
Try both tiers inside the Gemini API or Google AI Studio — moving between Gemini 3.8 Flash TTS and Flash-Lite TTS only takes a new model identifier. Weigh batch against priority inference before you lock in a production budget.