Gemini 3.8 Flash TTS
Latest GeminiFlagship text-to-speech model for expressive, studio-grade voices and long-form multi-speaker audio
- Price per 1M tokens
- $0.5 / $9 input / output · Google
- Context window
- 8.2K tokens in · 16.4K out
- Since the last one
- 160 days after Gemini 3.1 Flash TTS Preview
Since Gemini 3.1 Flash TTS Preview
3 releases in the Gemini line.
Gemini 2.5 Flash TTSSep 30, 2025197dGemini 3.1 Flash TTS PreviewApr 15, 2026160dGemini 3.8 Flash TTSSep 22, 2026
Released160 days later
Price in / out$0.5 / $9−54%
Context8.2Ksame
BENCHMARKS
Not in the Epoch Capabilities Index. Epoch benchmarks what it can run, so this is a gap in coverage, not a poor result.
Google's past year
38 release days in the past year, about one every 10 days. The next is expected around Oct 31, 2026. Forecasts ↗
NovDecJanFebMarAprMayJunJulAugSepOct
Specifications
RELEASE DATESep 22, 2026
WEIGHTSClosed weights
CONTEXT WINDOW8.2K
MAX OUTPUT16.4K
REASONINGNot listed
TOOL CALLINGNot listed
INPUTStext
OUTPUTSaudio/wav, audio/l16, audio/mulaw, audio/alaw
Specifications and prices from Models.dev; availability and limits may differ by provider. Benchmarks from Epoch AI (CC BY 4.0), LiveBench and the other sources named above.