Google Gemini 3.8 Flash-Lite Text to Speech is Google's high-throughput speech model released in September 2026, the lightweight sibling of Gemini 3.8 Flash Text to Speech: faster to respond and well suited to bulk content production and real-time conversational voice agents. It reads your text aloud word for word as natural, fluent speech and detects the input language automatically across more than 100 languages. Pick one of 30 prebuilt voices from the dropdown, each with its own character such as bright, firm, warm or informative, and choose the spoken language from the second dropdown (auto-detect by default). The model treats your text as a verbatim transcript, so put delivery instructions on the first line starting with "Style:", for example "Style: calm and steady" or "Style: upbeat and lively", and the model adjusts emotion, pace and tone accordingly; angle-bracket tags such as <laugh> or <short pause> add a laugh or a pause at that exact point. Great for customer-service prompts, announcements, short-video narration, course reading and accessibility audio. When you need studio-grade fidelity and more refined prosody, switch to Gemini 3.8 Flash Text to Speech. Text input is limited to 8,192 tokens and the audio is delivered as MP3. Maximum context window (input and output combined): about 24,576 tokens. Maximum total input per request (including history): 8,192 tokens. Maximum output per reply: about 16,384 tokens (model reasoning, if any, counts toward this limit). Output content formats: Audio Pricing: Medium Audio output format: MP3. This module does not support continuous conversations. AI can make mistakes. Please verify important information.