Available now

Gemini 3.8 Flash Lite TTS: text to speech

By Google

Gemini 3.8 Flash Lite TTS from Google reads text in a prebuilt voice or turns a two-speaker script into one dialogue track.

Model ID
Maker
Google
Added
September 29, 2026

Input

Fields marked * are required. Review the price before generating.

Verbatim text for single-speaker speech. For dialogue, omit prompt and provide speakers and turns instead. The complete input is limited to 8,192 tokens.

Example prompt. Edit it or write your own.

Additional settings

Delivery style, separate from the spoken transcript. Applies to all turns unless overridden.

Prebuilt voice for single-speaker speech.

Exactly two distinct speaker aliases and their prebuilt voices for dialogue.

Ordered dialogue turns, each identifying a configured speaker.

Price$0.05 / run

You sign up first. Your settings are kept.

About this model

Overview

Gemini 3.8 Flash Lite TTS has the same inputs as Gemini 3.8 Flash TTS. Write the words to be spoken in the prompt, choose a voice such as Aoede, Fenrir or Zephyr, and describe the tone separately in the style field. A <laugh> or <sigh> in the text adds that sound.

To make a conversation, skip the prompt, set up two speakers with a voice each and write the turns in order; a turn can have its own style direction.

What you can build

  • Short tutorial voice-overs
  • Back and forth explainers between two voices
  • Spoken notifications and app messages
  • Practice dialogues for language lessons

Prompting tips

  • Write only what should be heard in the prompt; tone and pace go in the style field.
  • Use short turns in a dialogue so the exchange keeps moving.
  • Try the same script with two or three voices before settling on one.

What to check

Compare pronunciation and pauses throughout. Measure turnaround time and quote; the Lite name alone does not establish a cost or quality advantage.

Inputs

  • Prompt (optional): Verbatim text for single-speaker speech. For dialogue, omit prompt and provide speakers and turns instead. The complete input is limited to 8,192 tokens.
  • Style Instructions (optional): Delivery style, separate from the spoken transcript. Applies to all turns unless overridden.
  • Voice (optional): Prebuilt voice for single-speaker speech. Options: Achernar, Achird, Algenib, Algieba, Alnilam, Aoede, Autonoe, Callirrhoe, Charon, Despina, Enceladus, Erinome, Fenrir, Gacrux, Iapetus, Kore, Laomedeia, Leda, Orus, Pulcherrima, Puck, Rasalgethi, Sadachbia, Sadaltager, Schedar, Sulafat, Umbriel, Vindemiatrix, Zephyr, Zubenelgenubi.
  • Speakers (optional): Exactly two distinct speaker aliases and their prebuilt voices for dialogue.
  • Turns (optional): Ordered dialogue turns, each identifying a configured speaker.

Output and limits

  • Sung or spoken words can come out unclear or differ from your text.
  • Exact length, tempo and key are not guaranteed; listen to the whole result before you use it.
  • Prompts that name real artists or protected songs can be refused.
  • Some prompts or outputs can be refused by safety checks.

Price guide

  • up to · 1,000 ASCII characters: $0.05 / run