Hello Gemini API team,
I’m a Spanish teacher building an educational app in Google AI Studio (an interactive historical-character interview tool for high school students) that relies on Gemini’s voice models so students can practice listening comprehension in Spanish.
Project number: 731706080..
Models requested:
- gemini-3.1-flash-tts-preview
- gemini-3.1-flash-live-preview
Observed behavior:
- Standard text generation models (gemini-2.5-flash, gemini-2.0-flash) work correctly with this same API key/project.
- Calls to gemini-3.1-flash-tts-preview via generateContent consistently return HTTP 403 PERMISSION_DENIED.
- The same 403 occurs when connecting to gemini-3.1-flash-live-preview via the Live API.
Could you please review my project and grant access to these preview voice models, or let me know what additional step is needed on my end? This app is intended for classroom use with students, so voice output is an essential accessibility feature, not a nice-to-have.
Thank you very much for your help.
Silvia Moline