Overview
NVIDIA® Riva is a set of GPU-accelerated multilingual speech and translation microservices for building fully customizable, real-time conversational AI pipelines. Riva includes automatic speech recognition (ASR), text-to-speech (TTS), and neural machine translation (NMT) and is deployable in all clouds, in data centers, at the edge, or on embedded devices. With Riva, organizations can add speech and translation capabilities with large language models (LLMs) and retrieved-augmented generation (RAG) to transform chatbots into powerful multilingual assistants and avatars. Riva is part of the NVIDIA AI Enterprise software platform, is available for $1 per GPU hour. Contact NVIDIA for special pricing for alternative GPU options or private offers. Link
Highlights
- Provides developers and AI practitioners with immediate world-class accuracy for 14 languages including Arabic, Chinese (Mandarin), English (US/UK), French, German, Hindi, Italian, Japanese, Korean, Portuguese, Russian, Spanish (LATAM/Spain) achieved with pretrained models trained on hundreds of thousands of hours of public and proprietary data.
- Delivers interactive responses in less than 300 milliseconds, and less then 100. milliseconds on embedded devices
- Riva is fully containerized and can easily scale to hundreds and thousands of real-time streams.
Details
Typical total price
$40.773/hour
Pricing
Instance type | Product cost/hour | EC2 cost/hour | Total/hour |
|---|---|---|---|
p3.2xlarge | $1.00 | $3.06 | $4.06 |
p3.8xlarge | $4.00 | $12.24 | $16.24 |
p3.16xlarge | $8.00 | $24.48 | $32.48 |
p3dn.24xlarge | $8.00 | $31.212 | $39.212 |
p4d.24xlarge Recommended | $8.00 | $32.773 | $40.773 |
g4dn.xlarge | $1.00 | $0.526 | $1.526 |
g4dn.2xlarge | $1.00 | $0.752 | $1.752 |
g4dn.4xlarge | $1.00 | $1.204 | $2.204 |
g4dn.8xlarge | $1.00 | $2.176 | $3.176 |
g4dn.12xlarge | $4.00 | $3.912 | $7.912 |
Additional AWS infrastructure costs
Type | Cost |
|---|---|
EBS General Purpose SSD (gp3) volumes | $0.08/per GB/month of provisioned storage |
Vendor refund policy
No refund
Legal
Vendor terms and conditions
Content disclaimer
Delivery details
64-bit (x86) Amazon Machine Image (AMI)
Amazon Machine Image (AMI)
An AMI is a virtual image that provides the information required to launch an instance. Amazon EC2 (Elastic Compute Cloud) instances are virtual servers on which you can run your applications and workloads, offering varying combinations of CPU, memory, storage, and networking resources. You can launch as many instances from as many different AMIs as you need.
Version release notes
Additional details
Usage instructions
Continue to Subscribe and launch the AMI on EC2 GPU instance following the prompts. Once the instance is launched, SSH into the instance.
Pull the NGC hosted Riva Quick Start scripts as follows: ngc registry resource download-version nvidia/riva/riva_quickstart:2.11.0
Follow the steps mentioned in the Quick Start Guide: https://docs.nvidia.com/deeplearning/riva/user-guide/docs/quick-start-guide.html
For accessing NVIDIA AI Enterprise Catalog: Run the identity token generation script: ./ngc-token.sh -g to print out the validation token. Copy the token and activate your NVIDIA AI Enterprise subscription at https://org.ngc.nvidia.com/activate .
NVIDIA AI containers from the Enterprise Catalog can be pulled once the account is activated.
For more information on NVIDIA AI Enterprise AMI please follow:
Quick Start Guide: https://docs.nvidia.com/ai-enterprise/deployment-guide-cloud/0.1.0/aws-ai-enterprise-vmi.html# AMI documentation and release notes: https://docs.nvidia.com/ngc/ngc-deploy-public-cloud/ngc-aws/index.html
Resources
Support
Vendor support
Global NVIDIA Support is included with purchase of NVIDIA Riva. Support requests are limited to 3 calls. For additional details on enterprise support, please refer the quick start guide.
With private pricing offers, customers are entitled to unlimited calls, and portal access for support.
Benefits of NVIDIA Enterprise Support include:
- Enterprise grade support and SLAs provided directly from NVIDIA
- Access to NVIDIA AI experts from 9am-5pm local business hours for guidance on configuration and performance
- Priority notifications for the latest security fixes and maintenance releases
- API stability and long-term support for up to 3 years on designated software branches
Upgrade Support Options also available with private pricing:
- Designated Technical Account Manager (TAM)
Support link:
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products
