Preserve OpenAI audio transcription output by hamedrabah · Pull Request #169 · braintrustdata/braintrust-sdk-java · GitHub
Skip to content

Preserve OpenAI audio transcription output - #169

Merged
Andrew Kent (realark) merged 1 commit into
braintrustdata:mainfrom
hamedrabah:fix/openai-audio-transcription-output
Aug 25, 2026
Merged

Preserve OpenAI audio transcription output#169
Andrew Kent (realark) merged 1 commit into
braintrustdata:mainfrom
hamedrabah:fix/openai-audio-transcription-output

Conversation

@hamedrabah

Copy link
Copy Markdown
Contributor

Closes #131.

Summary

  • recognize OpenAI transcription and translation responses by their text field
  • preserve the complete response object in braintrust.output_json, including verbose segments and words
  • keep existing choices/output precedence unchanged

Testing

  • ./gradlew :braintrust-sdk:test --tests dev.braintrust.instrumentation.InstrumentationSemConvTest
  • ./gradlew check

@hamedrabah

Copy link
Copy Markdown
Contributor Author

@realark

Copy link
Copy Markdown
Collaborator

@realark
Andrew Kent (realark) merged commit daaa975 into braintrustdata:main Aug 25, 2026
1 check passed
@realark Andrew Kent (realark) added the bug Something isn't working label Aug 27, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

bug Something isn't working

Projects

None yet

Development

Successfully merging this pull request may close these issues.

[bot] OpenAI audio transcription and speech spans missing braintrust.output_json

2 participants