v3.14
·
919 commits
to main
since this release
Release Notes
Voice Mode
New Features
- Transcriptions for Voice mode conversations now use the
whisper-1model instead ofgpt-4o-transcribe. (#873) - Input audio noise reduction for far-field microphones is enabled by default. (#874)
Deployment Information
| Schema Upgrade | Migration Script | Permissions Update | Task Definition Update | Configuration Update |
|---|---|---|---|---|
| No | No | No | No | No |
Deployment Details
- N/A
Related PRs
- feat(voice)/ Switch to
whisper-1for transcriptions by @ekassos in #873 - feat(voice)/ Add
far_fieldnoise reduction by @ekassos in #874
Full Changelog: 683-srv291-web176...685-srv293-web176