Skip to content

Conversation

@ubaid2751
Copy link

@ubaid2751 ubaid2751 commented Oct 1, 2025

Context

In latest version, the AudioTranscriptionConfig class was reduced to a placeholder,
which broke Gemini Live transcription (no config fields were passed to API).

What this PR does

  • Restores enable_output and enable_input fields in AudioTranscriptionConfig
    and AudioTranscriptionConfigDict.
  • Adds a test to verify field behavior.

Result

Gemini Live sessions can once again request input/output transcriptions,
consistent with v1.14 behavior.

✅ All existing tests pass.
✅ New test confirms config works.

@google-cla
Copy link

google-cla bot commented Oct 1, 2025

Thanks for your pull request! It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA).

View this failed invocation of the CLA check for more information.

For the most up to date status, view the checks section at the bottom of the pull request.

@janasangeetha janasangeetha self-assigned this Oct 3, 2025
@janasangeetha janasangeetha added the size:M Code changes between 10-40 lines label Oct 3, 2025
@ubaid2751
Copy link
Author

@janasangeetha Is this going forward ?

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

Labels

size:M Code changes between 10-40 lines

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants