Hello,
I am designing a program to teach the German language. I have generated many audio files for the lessons, but now I am getting this message:
“No audio generated.”
The text is short, yet it still cannot generate audio.
I have disabled the extensions,
cleared the cache,
and changed the browser,
but the problem still persists.
Hey @Wael_Alwasel — thanks for sharing the details, and sorry you’re running into this issue. It sounds like you’ve already done a solid round of troubleshooting!
A few things you might want to check or try next:
Text Formatting: Sometimes even short text can trigger issues if it contains special characters, emojis, or unsupported symbols. Try simplifying the input to plain text.
Rate Limits or Quotas: If you’ve generated a lot of audio files recently, you might be hitting a soft limit. Check your usage in the Google Cloud Console or Gemini dashboard.
Model Availability: Occasionally, specific models or endpoints may be temporarily down. Try switching to a different TTS model if available.
API Response Logs: If you’re using the API, inspect the response logs for any hidden error codes or warnings that might explain the failure.
Try a Different Account or Project: Sometimes project-level settings or permissions can interfere. Testing with a fresh project might help isolate the issue.
If none of that works, I’d recommend submitting a support ticket or posting in the Gemini API issue tracker with the exact text input and timestamp — that can help the team debug it faster.
Thanks for reaching us!
1 Like