Gemini 3.8 Flash-Lite TTS
Gemini 3.8 Flash-Lite TTS is Google's high-throughput text-to-speech model, documented as the replacement for gemini-3.1-flash-tts-preview.
Provider
Model family
Google Gemini
Text-to-speech
Cost tier
Tts Lite
Status
Current
Release Sep 23, 2026
Why teams choose it
Google documents this as the high-throughput lane beside Gemini 3.8 Flash TTS
not as a second copy of the studio model.
Caching, batch, flex, and priority inference are supported
Thinking, Live API, function calling, and search are not.
Tradeoffs to know
- No paid token rate for gemini-3.8-flash-lite-tts is published on the Gemini API pricing page checked September 30, 2026.
- It supports 101 languages, fewer than the 130 on Gemini 3.8 Flash TTS.
Technical specs
- Inputs
- text
- Outputs
- audio
- Capabilities
- text to speech, high throughput, 101 languages, caching, batch
- License
- Proprietary API
- API ID
gemini-3.8-flash-lite-tts- Source
- https://ai.google.dev/gemini-api/docs/models/gemini-3.8-flash-lite-tts
- Languages
- 101
- Input Token Limit
- 8,192
- Output Token Limit
- 16,384
Benchmarks
No independent or vendor benchmark scores in this catalog entry.
Google Gemini family lineup
Current models
Related models
Gemini 3.8 Flash-Lite TTS FAQ
What is Gemini 3.8 Flash-Lite TTS?
Gemini 3.8 Flash-Lite TTS is Google's high-throughput text-to-speech model, documented as the replacement for gemini-3.1-flash-tts-preview. The model code is gemini-3.8-flash-lite-tts. It takes text and returns audio, with an 8,192-token input limit, a 16,384-token output limit, and 101 languages. Google's Gemini API pricing page does not list a paid rate for this model ID.
When does Gemini 3.8 Flash-Lite TTS fit best?
High-volume speech generation
What should teams watch out for with Gemini 3.8 Flash-Lite TTS?
No paid token rate for gemini-3.8-flash-lite-tts is published on the Gemini API pricing page checked September 30, 2026.
Explore next
Models, tools, and comparisons that connect to this reference.