feat: mid-stream language_codes updates via updateConfiguration (v4.35.3)#160
Merged
Merged
Conversation
GitOrigin-RevId: e75527160d41d82d1fe4747445db14cd88af3b02
bgotthold-aai
force-pushed
the
BB87A999DDB72BAC88587A32C6D0C213
branch
from
c4d43c2 to
71cd15d
Compare
bgotthold-aai
changed the title
bgotthold-aai
changed the title
aleks-mitov
approved these changes
Jul 3, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Sync from the internal repo (2026/07/03), releasing v4.35.3 (includes the previously unsynced 4.35.1 and 4.35.2 changelog entries).
4.35.3
language_codesinupdateConfiguration()— re-steer the transcription language mid-stream without reconnecting:transcriber.updateConfiguration({ language_codes: ["es"] }). Pass[]to clear steering and restore the model's default multilingual code-switching (Universal-3.5 Pro Streaming only).4.35.2
opusandogg_opusstreamingencodingvalues — accepts compressed Opus audio (raw packet-per-message or Ogg-encapsulated).sampleRateis ignored for both; the Opus stream is self-describing.4.35.1
languageCodesstreaming parameter — steers transcription toward a set of languages (Universal-3.5 Pro Streaming only). Recommended replacement forlanguageCode, which is now deprecated but still supported.