OpenAI Speech Synthesis (SS) Plugin 1.2.0 to the UniMRCP Server (UMS) has been released.
The plugin is based on the following components:
- OpenAI Text-to-Speech REST 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-ss-1.7.2-1.el8.x86_64.rpm
- unimrcp-openai-ss-1.8.2-1.el8.x86_64.rpm
- Red Hat 9
- unimrcp-openai-ss-1.7.2-1.el9.x86_64.rpm
- unimrcp-openai-ss-1.8.2-1.el9.x86_64.rpm
- Ubuntu 22.04 LTS
- unimrcp-openai-ss_1.7.2-jammy_amd64.deb
- unimrcp-openai-ss_1.8.2-jammy_amd64.deb
- Ubuntu 24.04 LTS
- unimrcp-openai-ss_1.7.2-noble_amd64.deb
- unimrcp-openai-ss_1.8.2-noble_amd64.deb
This release adds support for instructions specified in the plugin configuration and/or via vendor-specific parameters used to guide the model on desired responses.
The detailed list of changes introduced in this release follows.
New Features
- Added support for instructions specified in the plugin configuration and/or via vendor-specific parameters used to guide the model on desired responses.
Fixed Problems
Configuration Parameters
- Added a new attribute 'instructions' to the element 'synth-settings'.
Miscellaneous
- Updated the Usage Guide to reflect the changes introduced in this release.
Visit the OpenAI SS plugin page for more information.
Thank you for using UniMRCP.
--
Arsen Chaloyan
Author of UniMRCP
http://www.unimrcp.org