Release Notes 4.1.0 & 4.1.1 & 4.1.2

Release date: 24th March 2023

Summary

This page highlights all the changes, new features and bugs addressed within the LumenVox Containers version 4.1.2 release. This change affects Speech products. This version is not available for Voice biometric products, this will be made available in upcoming releases. 

Highlights

1. Release of LumenVox API which replaces the Speech API and offers the following:

   1. Simplifies the product and API process

   2. Allow for higher throughput optimization

2. CPA & AMD are now handled via separate interaction APIs

3. Grammars are no longer required for CPA & AMD

4. ASR & Transcription have been separated into sperate interaction APIs. Transcription now makes use of phrase lists.

5. Configurations have been converted into protobufs

6. Improvements have been made to overall speech product stability and scalability

7. Final results are returned in session results

8. Partial results are disabled by default

9. Stereo audio is now catered for (this is only supported in WAV audio format)

10. Prometheus counters are now available

11. Structured container logging has been implemented

12. LumenVox API is now also available via MRCP (in addition to the existing gRPC interface)

13. Wav file format now supported

*Note: For TTS, we recommend that text not exceed 4mb (this is roughly 1300 Characters with spaces or around 250 words)

**Note: For Transcription, we recommend that users not exceed 90 minutes of transcribed audio due to gRPC size limits.

What’s new on LumenVox Cloud 4.1.2 

New Features

• MRCP interface is now enabled

• Prometheus counters added

• Structured logging implemented

• MRCP interface for LumenVox API added

• Stereo format enabled for speech products (only supported in WAV audio format)

• Wav file format now supported

• Session grammars implemented

Updates

• Improvements have been made to the following:

  1. Interaction Set Settings API has been removed

  2. Phrase lists implemented for Transcription 

  3. CPA & AMD output improved

  4. ASR now fully working

  5. Archiving & reporting updated for 4.1.2

  6. Updates made to protobufs including configuration changes

Installation notes

The following helm chart can be used

Helm Chart

Note that for MRCP there is no helm chart but a docker compose file. MRCP will run on its own Docker virtual machine which will integrate into the Kubernetes cluster.

Upgrade procedures

Upgrade or migration from previous versions is supported. Please contact LumenVox to discuss.

Updated API guide

APIs for all speech products available on version 4.1 can be obtained here: View full size LumenVox API Documentation 

Information for voice biometric products relates to version 3.4.0-3.4.3 

Model versions as part of the release

ASR - 2.6.0

TTS - 1.0 sample rate 22

VB - 2.1.13 (Note 2.1.15 for version 4.1.2)

VB incorporates Selene 2.4.3 which was integrated into the Container stack