Repository navigation
Conversation
spashii
added
the
preview
Contributor
|
Preview is up for
Updated on every push while the PR has the preview label. |
spashii
force-pushed
the
feat/final-transcript
branch
from
October 15, 2026 17:39
ceff993 to
ad72e59
Compare
spashii
force-pushed
the
feat/final-transcript
branch
from
October 15, 2026 17:50
052223c to
d395acb
Compare
…that switches language
…and says nothing after
…hisper's sentences stay beside the edits
…, counted per conversation
… piece with none ends at its quietest moment
…nly when it holds speech
… a gap again; final transcript, text pass and retries are on by default
This branch was successfully deployed
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
When a conversation finishes, one background job transcribes the whole recording again (Gemini or Whisper, set by LLM_FINAL_TRANSCRIPT, off by default) and that text is what the dashboard, summaries and chat read; the live text stays stored. The transcript page gets a sticky audio player that highlights the sentence being played, and Whisper can get one text pass that edits inside sentences only (LLM_FINAL_TEXT_PASS, off by default).