Google Speech Recognition (GSR) Plugin 1.33.1 to the UniMRCP Server (UMS) has been released.

The plugin is based on the following components:

• Google APIs 1.9.0
• gRPC 1.61.1
• Protobuf 25.1

The plugin supports the following Google Speech-to-Text API versions:

• v1
• v1p1beta1
• v2

The plugin is available for the following UMS versions:

• 1.7.0
• 1.8.0

The binaries are currently available for the following Linux distributions:

• Red Hat 8
  • unimrcp-gsr-1.7.23-1.el8.x86_64.rpm
  • unimrcp-gsr-1.8.10-1.el8.x86_64.rpm
• Red Hat 9
  • unimrcp-gsr-1.7.23-1.el9.x86_64.rpm
  • unimrcp-gsr-1.8.10-1.el9.x86_64.rpm
• Ubuntu 22.04 LTS
  • unimrcp-gsr_1.7.23-jammy_amd64.deb
  • unimrcp-gsr_1.8.10-jammy_amd64.deb
• Ubuntu 24.04 LTS
  • unimrcp-gsr_1.7.23-noble_amd64.deb
  • unimrcp-gsr_1.8.10-noble_amd64.deb

This release sets the Waveform-URI header field on the RECOGNITION-COMPLETE event even when recognition completes with no-input timeout. The release also fixes processing of the SPEECH_ACTIVITY_TIMEOUT event, if enabled, when the single-utterance parameter is false.

Visit the GSR plugin page for more information.

• https://unispeech.io/gsr
• https://www.unimrcp.org/gsr

Thank you for using UniMRCP.

--
Arsen Chaloyan
Author of UniMRCP
http://www.unimrcp.org