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
Google Dialogflow (GDF) Plugin 1.18.0 to the UniMRCP Server (UMS) has been released.
The plugin is based on the following components:
- UniMRCP Server 1.7.0
- Google APIs 1.4.0
- gRPC 1.30.2
- Protobuf 3.12.2
The plugin supports the following Dialogflow API versions:
- v2
- v2beta1
- v3
- v3beta1
The binaries are currently available for the following Linux distributions:
- Red Hat / CentOS 7 (unimrcp-gdf-1.7.5-1.el7.x86_64.rpm)
- Red Hat / CentOS 8 (unimrcp-gdf-1.7.5-1.el8.x86_64.rpm)
- Ubuntu 16.04 LTS (unimrcp-gdf_1.7.5-xenial_amd64.deb)
- Ubuntu 18.04 LTS (unimrcp-gdf_1.7.5-bionic_amd64.deb)
This release adds support for Dialogflow v3 API complimentary to v2, v2beta1 and v3beta1 APIs. The API version as well as Google account credentials can now be specified by the user application per MRCP session. The release is built against a newer version of Google APIs.
The support for region-based agents is limited in this release. Agents defined in the global region continue to be primarily supported.
New Features
- Added support for Dialogflow v3 API complimentary to v2, v2beta1 and v3beta1 APIs.
- Allow the user application to specify the parameters 'gapp-credentials-file', 'service-uri', 'api', 'location' per MRCP session. The parameters set in the first RECOGNIZE request are observed for creation of a gRPC channel.
- Made the input mode, set in NLMLS results for a triggered event, configurable. The mode can be set to 'speech' for the platforms not accepting the extended mode 'event'.
- Allow the CX agent identifier to be specified using meta data in SRGS XML similarly to other parameters.
- Set the location in the URI path, if used, for v2beta1, v3 and v3beta1 APIs.
Fixed Problems
- If the parameter 'generate-output-audio' is set to 'true', the audio output is enabled not only for regular speech requests but also for DTMFs and triggered events.
- Do not limit the content size to 4 Kb while composing the NLSML instance in JSON format. This is a regression introduced in 1.17.0 release.
Configuration Parameters
- Added a new attribute 'event-input-mode' to the element 'results'. The attribute defaults to 'event' and can be set to 'speech'.
- Added new attributes 'service-uri' and 'location' to the element 'streaming-recognition'.
Miscellaneous
- Upgraded Google APIs from unigoogleapis-1.3.0 to unigoogleapis-1.4.0.
- Updated the Usage Guide to reflect the changes introduced in this release.
Visit the GDF plugin page for more information.
Thank you for using UniMRCP.
--
Arsen Chaloyan
Author of UniMRCP
http://www.unimrcp.org
