fix: Honor stt_enabled config to disable voice transcription#1111
Closed
Jah-yee wants to merge 2 commits intoNousResearch:mainfrom
Closed
fix: Honor stt_enabled config to disable voice transcription#1111Jah-yee wants to merge 2 commits intoNousResearch:mainfrom
Jah-yee wants to merge 2 commits intoNousResearch:mainfrom
Conversation
added 2 commits
March 12, 2026 16:38
Allows users to override the hardcoded 900s timeout when using local LLM providers like Ollama or LM Studio. Fixes NousResearch#1010
- Add stt_enabled field to GatewayConfig (default: True) - Skip transcription and return placeholder message when disabled - Fixes issue where gateway ignores stt.enabled: false in config
|
duplicate #1110 |
Contributor
|
Superseded by PR #1394. The underlying The merged fix came from salvaging PR #1110 onto current Thanks for working on the issue. |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
This PR fixes the issue where the gateway ignores the
stt.enabled: falsesetting in config.yaml and always attempts to call OpenAI Whisper API for voice messages.Changes
gateway/config.py: Added
stt_enabledfield toGatewayConfigdataclass with default valueTrue(for backward compatibility)gateway/run.py: Added check for
stt_enabledconfig at the start of_enrich_message_with_transcription()method. When disabled, returns a placeholder message instead of attempting transcription.Fix
stt_enabled: false- skip transcription entirely when disabledstt_enabled: falsein their gateway config to disable voice transcriptionCloses #1100