Skip to content

fix: update google-generativeai version for response_modalities support#837

Open
pocper1 wants to merge 1 commit intoharry0703:mainfrom
pocper1:fix/update-google-generativeai
Open

fix: update google-generativeai version for response_modalities support#837
pocper1 wants to merge 1 commit intoharry0703:mainfrom
pocper1:fix/update-google-generativeai

Conversation

@pocper1
Copy link

@pocper1 pocper1 commented Mar 8, 2026

Summary

Fixes #836

The response_modalities field in GenerationConfig was introduced in a newer
version of the google-generativeai SDK. The version previously pinned in
requirements.txt was too old to support this field, causing Gemini TTS to fail
immediately with:

Unknown field for GenerationConfig: response_modalities

Changes

  • Updated google-generativeai to a minimum version that supports
    response_modalities in GenerationConfig

How to Test

  1. Set TTS provider to Gemini
  2. Select any voice (e.g. Zephyr)
  3. Start a task without a custom audio file
  4. Confirm audio generates successfully without Unknown field for GenerationConfig error

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

[Bug]: Gemini TTS failed - Unknown field for GenerationConfig: response_modalities

1 participant