---
id: "google/gemini-3.8-flash-lite-tts"
also: ["google/gemini-3.8-flash-lite-tts-20260922", "vercel/google/gemini-3.8-flash-lite-tts"]
cheapest_list_usd_per_m: "0.5 in, 6.0 out, at google-ai-studio on openrouter"
cheapest_effective_usd_per_m: "0.4935 in, 6.0 out, at google-ai-studio on openrouter"
context: 32768
max_output: 16384
input: ["text"]
output: ["speech"]
released: "2026-09-23"
api: ["/api/v1/audio/speech"]
params: ["include_reasoning", "max_tokens", "reasoning", "stop", "temperature"]
endpoints: 4
gateways: "openrouter (2), vercel (2)"
no_training: 3
trains: 0
retains_prompts: 1
---
# Google: Gemini 3.8 Flash Lite TTS

Gemini 3.8 Flash-Lite TTS is Google's preview text-to-speech model for low-latency, high-volume speech generation in 101 languages. It supports single- and multi-speaker speech, streaming synthesis, and style direction using the same request schema as Gemini 3.8 Flash TTS. Prebuilt and curated voices, voice design, and voice replication support read-aloud features and conversational voice agents.