UI Bug: Audio Settings dropdowns (Pace, Accent, Voice Style) not selecting or applying in Google AI Studio

Google AI Studio
, ,
1

Hi Team,

I am facing a severe UI bug in Google AI Studio while configuring Audio settings for Text-to-Speech / Audio Generation.

Issue Details:

  1. When attempting to select options in the Audio Settings dropdowns—such as Voice Style (e.g., Newscaster), Pace (e.g., Rapid Fire), or Accent (e.g., American General, British)—the UI fails to update or select the chosen option.
  2. The options click, but the selected option does not move up or register into the active setting field.
  3. As a result, the generated audio defaults to standard tone/accent without reflecting any of the user-selected audio configurations.

Troubleshooting Already Done:

  • Tested across multiple Google accounts (same issue persists on other accounts as well).
  • Tested on different browsers / Incognito mode.

This issue started happening yesterday and prevents full control over audio customization. Kindly investigate and fix this UI regression.

Thank you!

Screenshot 2026-09-21 111841
Screenshot 2026-09-21 111841688×887 35.2 KB

2

Hello @tripathi_abhijeet,

The Style, Pace, and Accent dropdown controls in the Speech Playground are active and pass the selected values in the generation request. If a starter template or existing session retains previous speaker settings, reset the configuration in the Run settings panel using Reset default settings, or start a clean session from Create new dialog.

We also recommend trying the latest Gemini text-to-speech models in the Speech Playground or via the API — Gemini 3.8 Flash TTS (gemini-3.8-flash-tts) and Gemini 3.8 Flash-Lite TTS (gemini-3.8-flash-lite-tts), which replaces gemini-3.1-flash-tts-preview (see the Text-to-speech generation guide).

Please retry and let us know if the issue persists.