Gemini 3.8 Flash Lite TTS Reaches General Availability
Google announced the general availability of Gemini 3.8 Flash Lite TTS on September 22, 2026.
Official Announcement Details
The official changelog records that Google made Gemini 3.8 Flash Lite TTS generally available on September 22, 2026. This release includes the next-generation text-to-speech audio models and the Gemini API Voices endpoint located at /v1beta/voices. The specific model identifier is gemini-3.8-flash-lite-tts.
- Event date: September 22, 2026
- Model status: Generally Available (GA)
- API Endpoint: /v1beta/voices
Documented Specifications and Scope
According to the provided facts, the model accepts text input and produces audio output. It features a context window of 8,192 tokens and a maximum output of 16,384 tokens. The source describes the model as fast and cost-efficient, specifically built to replace gemini-3.1-flash-tts-preview. It is intended for high-throughput production and real-time voice agent cascades. Open weights are not confirmed for this release.
- Input modality: Text
- Output modality: Audio
- Context window: 8,192 tokens
- Max output tokens: 16,384 tokens
Evaluation Procedure for Engineers
To evaluate the model, engineers should define specific test cases representing their target use cases, such as long-form narration or short conversational responses. Measure the latency and audio quality against the previous preview model, gemini-3.1-flash-tts-preview. Compare the cost per token if pricing data becomes available through official channels. Validate that the output meets specific technical requirements for your application's integration layer. Note that the source does not provide benchmark scores, specific pricing figures, or architectural details regarding local installation capabilities.
- Test with representative text inputs
- Measure response time and audio fidelity
- Compare performance metrics with gemini-3.1-flash-tts-preview
- Validate integration compatibility with existing systems
Primary sources
Frequently asked questions
What is the primary purpose of Gemini 3.8 Flash Lite TTS?
The source states it is a fast, cost-efficient text-to-speech model built to replace gemini-3.1-flash-tts-preview for high-throughput production and real-time voice agent cascades.
Does the source confirm open-weight access?
No. The fact sheet indicates openWeights=false, which records that open weights are not confirmed. It does not establish whether local installation is possible or impossible.