fal-ai/gemini-3.1-flash-tts

Newest audio model from Google introduces granular audio tags that give you precise control to direct AI speech for expressive audio generation.

Inference

Commercial use

Partner

Schema

LLMs

Playground API Examples

Open in Sandbox

Input

Prompt*

Host: Welcome back to AI Frontiers. Dr. Chen, I heard some big news dropped today. What's going on? DrChen: [excited] Gemini TTS just went live on fal.ai. Google's text to speech model, fully available through fal's API right now. Host: Wait, seriously? That's Google's multi-speaker TTS right? DrChen: Yep. You write your script with speaker tags, add style instructions, and it generates a natural sounding conversation. Two distinct voices, emotional cues, the whole thing. Host: How does it sound? DrChen: Really good. The voices have genuine character to them. You can tell the model understands context, not just words. And it supports over 80 languages at the same quality level. Host: That's wild. So how do people get started? DrChen: Just head to fal.ai, find Gemini TTS, write a conversation, and hit run. It's that simple. Host: [laughing] Love it. Short and sweet. Thanks Dr. Chen! DrChen: Anytime.

Voice

Additional Settings

Customize your input with more control.

Result

Idle

What would you like to do next?

Download

{
  "audio": {
    "url": "https://v3b.fal.media/files/b/0a967e9a/Q5ohyfX_OIfppEtdf1G9a_gemini_31_flash_tts_output.mp3",
    "file_name": "gemini_31_flash_tts_output.mp3",
    "file_size": 954285,
    "content_type": "audio/mpeg"
  }
}

Your request will cost $0.05 per 1000 character.