NVIDIA® Riva, part of the NVIDIA AI platform, is a GPU-accelerated speech AI SDK for building and deploying fully customizable, real-time AI pipelines that deliver world-class accuracy in all clouds, on premises, at the edge, and on embedded devices.

Download now Introductory resources Documentation

Ways to Get Started With NVIDIA Riva

Riva Enterprise for Deployment at Scale

Purchase Riva Enterprise for Deployment at Scale

Get unlimited usage on all clouds, access to NVIDIA AI experts, and long-term support for large-scale deployments of Riva with NVIDIA Riva Enterprise software.

Try Riva Enterprise for Free on NVIDIA LaunchPad

Contact Us to Learn More About Purchasing Riva Enterprise
Riva AI Workflows

Get Access to Riva AI Workflows

Accelerate development time with packaged AI workflows for audio transcription and intelligent virtual assistants, available with NVIDIA Riva Enterprise software.

Learn More About the Transcription Workflow

Learn More About the Intelligent Virtual Assistant Workflow
Containers and Models for Development

Download Containers and Models for Development

Develop voice-enabled applications for cloud, data center, or embedded deployments with Riva containers and pretrained models, available for free on NVIDIA NGC™ to members of the NVIDIA Developer Program.

Download Now for Cloud and Data Center

Download Now for Embedded

Introductory Resources

Quick-Start Guide

Get step-by-step instructions for deploying pretrained models as services on a local workstation and how to interact with them through a client.

Get Started

Introductory Blog

Learn about Riva’s architecture, key features, and components for building speech AI services.

Read Blog

Introductory Webinar

Build and deploy end-to-end speech AI pipelines using NVIDIA Riva.

Watch Webinar

Development Starter Kits

Access everything you need to start developing your speech AI application with NVIDIA Riva containers and models, including tutorials, notebooks, forums, release notes, and documentation.

Automatic Speech Recognition

Achieve high transcription accuracy for English, Spanish, Mandarin, Hindi, Russian, Korean, German, Portuguese, and French and two out-of-the-box expressive professional female and male voices for U.S. English with state-of-the-art models pretrained on thousands of hours of audio on NVIDIA supercomputers.

  • Speech Recognition Documentation
  • Quick Start Guide
  • Tutorial: Use Riva ASR Out-Of-The-Box
  • Tutorial: Riva ASR Customization
  • Sample App: Riva Contact
  • Sample App: Virtual Assistant with Rasa

Get Started


Customize across ASR pipelines for different languages, accents, domains, vocabulary, and context for the best possible accuracy for your use case, and across TTS pipelines for the voice and intonation you want.

  • TTS Documentation
  • Quick Start Guide
  • Documentation: TTS Service Sample
  • Documentation: TTS SSML Sample
  • Sample App: Virtual Assistant with RASA

Get Started

End-to-End Testing and Prototyping for Deployment

Explore free NVIDIA LaunchPad labs that let you test and prototype your speech AI-based solutions in the same high-performance NVIDIA Riva software stack that’s deployable today.

Customizing Text-to-Speech With NVIDIA Riva

Interact With Real-Time Speech AI APIs

Take This Lab
Transcription and Intelligent Virtual Assistant

Customizing ASR With NVIDIA Riva

Take This Lab
Interact with Real-Time Speech AI APIs

Customizing Text-to-Speech With NVIDIA Riva

Take This Lab
Intelligent Virtual Assistant

Intelligent Virtual Assistant

Take This Lab
Audio Transcription

Audio Transcription

Take This Lab

Early Access Programs

Riva Studio

Riva Studio is a low-code service that simplifies and accelerates the creation, customization, and deployment of enterprise speech AI applications.

Apply for Early Access

Bot Maker

NVIDIA Bot Maker is an SDK that enables you to build conversational AI applications such as chatbots, multimodal virtual assistants, and interactive avatars.

Apply for Early Access
Ethical AI

NVIDIA platforms and application frameworks enable developers to build a wide array of AI applications. Consider potential algorithmic bias when choosing or creating the models being deployed. Also, work with the model’s developer to ensure that it meets the requirements for the relevant industry and use case; that the necessary instruction and documentation are provided to understand error rates, confidence intervals, and results; and that the model is being used under the conditions and in the manner intended.

Stay up to date on the latest speech AI news from NVIDIA

Sign Up