Riva Enterprise¶

From version 2.0 onwards, Riva is free of charge for both development and production use up to a daily usage limit. For enterprises looking to deploy at a scale above the daily usage limit for ASR and TTS, we announced Riva Enterprise, a paid offering that includes NVIDIA enterprise support.

Riva Enterprise includes:

Annual usage license of Riva ASR and TTS on all cloud and on-prem platforms
Access to NVIDIA AI experts with enterprise business support for deployment, configuration, and performance questions
Support for all recent releases to control your maintenance and upgrade schedule
Priority access to new languages, software patches, upgrades, and maintenance releases

NVIDIA Riva Enterprise Short Term Supported Release(s)¶

The Short Term Support (STS) offering of NVIDIA Riva Enterprise provides top of tree AI innovations for teams building services and products leveraging NVIDIA Riva Enterprise. Service providers, ISVs and other organizations can leverage this program to access NVIDIA support for releases in the last 6 months starting with NVIDIA Riva 2.0. Release notes for releases in the last 6 months can be found here.

Configuration¶

To enable Riva Enterprise metrics collection when deploying a Riva Skills container, set three environment variables:

RIVA_API_KEY must be set to the NGC API Key associated with your account
RIVA_API_NGC_ORG must be set to the organization or organization/team within NGC to associate metrics with. The organization must be one you are a member of.
RIVA_EULA must be set to accept to acknowledge that you have read and agree to the terms specified in the Riva End User License Agreement.

Important

The Riva server will not start if the API Key is specified but the EULA is not accepted or an organization is not supplied.

Quickstart¶

The Quickstart deployment path can be used for testing Riva Enterprise. See the Docker deployment configuration section for complete details of configuration options available. Within config.sh, uncomment the Enterprise section and fill in variables appropriately:

# Enable Riva Enterprise
# If enrolled in Enterprise, enable Riva Enterprise by setting configuration
# here. You must explicitly acknowledge you have read and agree to the EULA.
RIVA_API_KEY=<ngc api key>
RIVA_API_NGC_ORG=<ngc organization>
RIVA_EULA=accept

Helm¶

The Helm deployment path can also be used for testing Riva Enterprise. See the Kubernetes deployment page for complete details of configuration options available. Within values.yaml, enable the Enterprise section and fill in variables appropriately:

rivaEnterprise:
  ngcSecret: rivadeploysecret
  ngcOrg: your_org_name
  acceptEula: "accept"
  enabled: true

Frequently Asked Questions¶

For Riva ASR, how is usage measured?

Riva ASR usage is based on the amount of speech audio successfully processed (not including audio that does not contain speech). The Riva VAD algorithm described in Beginning/End of Utterance Detection is used to detect periods of speech vs non-speech.

For Riva TTS, how is usage measured?

Riva TTS usage is based on the number of characters sent to the service to be synthesized.

NVIDIA Riva Skills

Riva Enterprise

Contents