feat(stt): echo transcript to user after voice recording - #40810
Closed
freqyfreqy wants to merge 1 commit into
Closed
feat(stt): echo transcript to user after voice recording#40810freqyfreqy wants to merge 1 commit into
freqyfreqy wants to merge 1 commit into
Conversation
…tion
Add configurable stt.echo_transcript option (default: true) that sends
the transcribed text back to the user as a separate message after
processing a voice memo. This gives users a readable record of their
voice input in the chat history for future reference.
The feature is configurable via config.yaml:
stt:
echo_transcript: true # default, set false to disable
Includes:
- GatewayConfig.stt_echo_transcript field with YAML round-trip support
- Backwards-compatible config loading (stt.echo_transcript or
stt_echo_transcript top-level)
- Regex extraction that handles both voice message formats
- Guard against empty transcripts
Contributor
Author
|
Another reason this is useful is because have a voice transcript in the chat helps searching in the session for humans to understand previous context. |
alt-glitch
added
type/feature
Collaborator
Contributor
|
Implemented on main: voice-message transcripts are echoed back to the user in the 🎙️ format at every gateway path, and as of PR #58859 the behavior is configurable via |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What this does
When voice/STT recording completes, echo the transcribed text back to the user so they can verify what was captured before the agent processes it.
Why
Users need confirmation that the speech-to-text pipeline captured their intent correctly, especially with voice commands or dictation. Without echo, silent failures in ASR can cause the agent to act on garbled/incorrect input without the user realizing it.
Changes