OpenAI Speech Recognition (SR) Plugin 1.1.0 to the UniMRCP Server (UMS) has been released.
The plugin is based on the following components:
- OpenAI Realtime Transcription WebSocket API
- Libevent 2.1.9
- Rapidjson 1.1.0
The plugin is available for the following UMS versions:
The binaries are currently available for the following Linux distributions:
- Red Hat 8
- unimrcp-openai-sr-1.7.1-1.el8.x86_64.rpm
- unimrcp-openai-sr-1.8.1-1.el8.x86_64.rpm
- Red Hat 9
- unimrcp-openai-sr-1.7.1-1.el9.x86_64.rpm
- unimrcp-openai-sr-1.8.1-1.el9.x86_64.rpm
- Ubuntu 20.04 LTS
- unimrcp-openai-sr_1.7.1-focal_amd64.deb
- unimrcp-openai-sr_1.8.1-focal_amd64.deb
- Ubuntu 22.04 LTS
- unimrcp-openai-sr_1.7.1-jammy_amd64.deb
- unimrcp-openai-sr_1.8.1-jammy_amd64.deb
This release introduces support for various auth methods. The release also provides a few fixes and improvements.
The detailed list of changes introduced in this release follows.
New Features
- Added detailed time metrics to RDRs.
- Added support for various auth methods including bearer token specified in Authorization header or auth-key specified as header or query param.
Fixed Problems
Configuration Parameters
- Added a new attribute 'auth-method' to the element 'openai-settings'
Miscellaneous
- Updated the Usage Guide to reflect the changes introduced in this release.
Visit the OpenAI SR plugin page for more information.
Thank you for using UniMRCP.
--
Arsen Chaloyan
Author of UniMRCP
http://www.unimrcp.org
Downloads
Repository
Documentation
Issues
Project Media
Google Cloud
Microsoft Azure
Amazon
Nuance Mix
OpenAI
SoundHound
IBM Watson
NVIDIA
Verbio
Deepgram
Yandex Cloud
Speechmatics
ASAPP
GoVivace
Voci
Kaldi
Platforms
Announcement Group