Request allowlist access for audio output in Gemini (Vertex AI)

Hello Google AI Team,

I am requesting to have my Google Cloud Project allowlisted for the Vertex AI Gemini Text-to-Speech (Audio Output) capabilities.

We are currently building a production media application and successfully use Vertex AI for text generation. However, when attempting to generate speech/audio via the Vertex AI API (e.g. gemini-2.5-flash-preview-tts and gemini-2.0-flash), we receive the 400 error: “You are not allowlisted to request audio output.”

Could you please whitelist our project so we can fully migrate our audio generation workload to Vertex AI?

Project Details:

  • Primary Use Case: Text-to-Speech generation

Thank you very much for your help!

Hi, have you tried gemini-2.5-flash-tts?

See Gemini-TTS  |  Cloud Text-to-Speech  |  Google Cloud Documentation