Skip to main content

Gemini TTS — 30 voices + Style Prompt

Uses Gemini TTS from Google AI Studio with 30 voices, each with a descriptor (Bright, Upbeat, Firm, …), plus a "style prompt" you can use to direct delivery — like "Say cheerfully" or "Speak excitedly".

What it does​

  • Pick from 30 voices, each with a personality descriptor
  • Use a style prompt to direct the emotional delivery
  • Supports both Flash (fast) and Pro (higher quality) models
  • Uses an API key from Google AI Studio

Where to find it​

Settings → Connections → Gemini (API key) + Settings → TTS Voice → Provider = Gemini

Settings → TTS Voice → Gemini page showing the 30-voice dropdown and style prompt field
Pick a voice + add a style prompt

Inputs / configurable settings​

  • Gemini API Key
  • Model — Flash / Pro
  • Voice name — one of 30 options
  • Style prompt — e.g. "Speak cheerfully", "Say with excitement"

Use case​

A streamer with high-energy content — set the style prompt to "Speak cheerfully like a hype girl cheering on the team" and Gemini will read every donation in that exact vibe — something no other provider can do.