# Gemini 3.8 Flash TTS Models on fal

By Steven Van · 2026-09-25

Gemini 3.8 Flash TTS and Flash Lite TTS bring 30 voices and text-based delivery direction to fal's API.

fal added Gemini 3.8 Flash TTS and Flash Lite TTS, two text-to-speech models for generating expressive speech. Both support voice and delivery direction through text prompts, covering pacing, emotion, dialect, and conversational cues, so a creator can shape how a line is read rather than just what it says.

The models offer 30 voices and can produce single-speaker narration or two-speaker dialogue. They're available now through the [fal API](<https://fal.ai/models/google/gemini-3.8-flash-tts/api>), alongside other models on the [fal](<https://creatorstoolbox.com/tools/fal>) platform.

[View media](<https://video.twimg.com/ext_tw_video/2103566071940669441/pu/vid/avc1/1280x720/HYSDJ5qI21dVzIhp.mp4?tag=12>)

![fal](<https://fal.ai/icon-512.png>)

fal

A generative media platform and inference API for running fast image, video, and audio AI models at scale.

[View fal →](<https://creatorstoolbox.com/tools/fal>)

[Read the original announcement →](<https://x.com/i/status/2103566129776009266>)

[Read Gemini 3.8 Flash TTS Models on fal on Creators Toolbox](<https://creatorstoolbox.com/blog/fal-gemini-3-8-flash-tts-models-on-fal>)

---
Canonical source: https://creatorstoolbox.com/blog/fal-gemini-3-8-flash-tts-models-on-fal