Gemini-3.8-flash-tts returning HTTP 429 ("Google voiceover was rejected") with no recognized quota category

Gemini API
1

When invoking the gemini-3.8-flash-tts speech model for audio generation, requests fail intermittently with an HTTP 429 Too Many Requests error. The accompanying error message reads:

“Google voiceover was rejected (HTTP 429). Google did not supply a recognized quota category. Check this speech model’s usage and limits in Google AI Studio. Completed recordings are saved.”

Observed Behavior:

  • The error suggests checking usage limits in Google AI Studio, but the Google AI Studio Rate Limits dashboard does not explicitly map a specific or recognized quota line item for gemini-3.8-flash-tts voiceover generation.

  • Standard metrics (RPM, TPM, RPD) for Tier 2 show peak usage well below project capacity ceilings, but the TTS endpoint still rejects requests with code 429.

  • The API payload returns standard HTTP 429 without referencing a clear quota category identifier (e.g., RESOURCE_EXHAUSTED / specific limit type).

Environment & Setup:

  • Model: gemini-3.8-flash-tts

  • Account Tier: Tier 2 (Paid Google AI Studio Project)

  • API / Endpoint: Voiceover / Text-to-Speech Generation

Questions / Request:

  1. Is gemini-3.8-flash-tts subject to an unlisted audio token rate limit or a separate regional concurrency pool limit?

  2. Why is no recognized quota category returned in the HTTP 429 response body?

  3. How can we properly track and manage limits for speech/voiceover models in the AI Studio Dashboard to avoid unexpected request rejections?

image
image2780×1580 220 KB

image
image2790×942 166 KB

2

Hi @Arun_kumar_Anala! We’ve addressed this issue - can you please let me know if you continue getting 429s? Thank you!

3

Rate limit exceeded for model gemini-3.8-flash-tts (limit: 100 requests per day on Tier 1). Please retry in 17h27m55s or upgrade your tier at https://ai.dev/rate-limit.

Just not got this error.

it’s not resolved . kindly help.

4

Screenshot 2026-10-01 at 11.16.01 AM
Screenshot 2026-10-01 at 11.16.01 AM3384×1804 386 KB

Rate limit exceeded for model gemini-3.8-flash-lite-tts (limit: 100 requests per day on Tier 1). Please retry in 18h44m24s or upgrade your tier at https://ai.dev/rate-limit.

Hi Team, I am facing the same rate-limit issue again today, and it now appears to be recurring on a daily basis. Although my account is on Tier 2, the API is still getting capped at 100 requests per day.

This is significantly impacting and delaying the project I am currently working on, as I rely on this API for regular processing. I am not sure why the Tier 2 limits are not being applied correctly to my account.

Could you please investigate this issue on priority and help resolve it at the earliest? Any urgent assistance would be greatly appreciated, as this recurring limitation is affecting my project timelines.

Thank you for your support.

5

Error: Rate limit exceeded for model gemini-3.8-flash-lite-tts (limit: 100 requests per day on Tier 1). Please retry in 18h19m51s or upgrade your tier at https://ai.dev/rate-limit.

I encountered the same error again today. It appears that the quota resets around 1:30 PM IST.

6

Hello @Arun_kumar_Anala ,

DM’ed you for more details.

7

Hi @Sai_Deepika_K , Here is the project details:

Project details

Name
Default Gemini Project

Project name
projects/457014870…

Project number
457014870..

Project id
gen-lang-client-035241..