googleReleased Sep 23, 2026

Google: Gemini 3.8 Flash Lite TTS

Separate spoken text from delivery instructions, or script a two-voice dialogue with per-turn style overrides.

Source description

Gemini 3.8 Flash Lite TTS is a text-to-speech model from Google and the fast, high-throughput member of the 3.8 TTS family alongside Gemini 3.8 Flash TTS. It is suited for...

Context window32.8K
Max output16.4K
Provider endpoints1
Benchmark results1
Measured performance

Benchmark results

All leaderboards ↗
AA Provider Voice TTS Arena ↗Unversioned · provider native voices
1,247.72

Provider native voices · all categories · US + UK accents · 8 listed voices

95% CI 1,233.72–1,261.72 · n=2,776

Independent result
Access & cost

Prices across providers

1 quote
Rate
$0.03
USD / 1K characters
Price source ↗Checked Oct 18, 2026
Endpoint IDgoogle/gemini-3.8-flash-lite-tts

Model specifications

Developer
google
Modality
Audio
Context
32,768 tokens
Maximum output
16,384 tokens
Weights
Not reported
Released
Sep 23, 2026
Provider listed
Sep 23, 2026
First discovered
Oct 16, 2026

Exact identities

  • openroutergoogle/gemini-3.8-flash-lite-tts
  • falgoogle/gemini-3.8-flash-lite-tts
  • aa-tts0bacd380-cb3b-4fc9-956d-dd50711ba8bf

Sources

Updated Oct 18, 2026

More from google

View all ↗
googleListed 28 days ago

Lyria 3.5

Lyria 3.5 is Google DeepMind's latest music generation model, and you can generate almost any type of music with it

No reported score
No reported score
Listed from $0.10/ generation · USDfal
googleListed Apr 24

Google: Gemini 3.1 Flash TTS Preview

Gemini 3.1 Flash TTS Preview is a text-to-speech model from Google, and a substantial generational step up from Gemini 2.5 Flash TTS. It takes text input and produces audio output...

32.8K contextNo reported score
No reported score
Price not listed
googleListed Mar 30

Google: Lyria 3 Pro Preview

Full-length songs are priced at $0.08 per song. Lyria 3 is Google's family of music generation models, available through the Gemini API. With Lyria 3, you can generate high-quality, 48kHz...

1M contextImage inputStructured outputNo reported score
No reported score
Price not listed