Speech and Translation AI
NVIDIA Riva
Create customizable, easy-to-integrate AI voice teammates with seamless, real-time communication capabilities enabled with multilingual speech, transcription, and translation AI.
Overview
What Is NVIDIA Riva?
NVIDIA® Riva is a collection of GPU-accelerated multilingual speech and translation microservices for building fully customizable, real-time conversational AI pipelines. Riva includesindustry leading 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, and on embedded devices. With Riva, organizations can add speech and translation interfaces that transform chatbots into engaging, expressive multilingual voice AI agents or avatars.
NVIDIA Riva Canary Now Available
Riva Canary is a set of multilingual, multi-tasking models that can be deployed as NVIDIA NIM™ microservices. They support automatic speech-to-text recognition and speech-to-text translation, can add punctuation and capitalization, and support translation.
NVIDIA Riva Magpie TTS Available Now
Riva Magpie TTS converts text into audio and features both male and female natural-sounding, multilingual speech. The model can be customized with additional, brand-specific voices and is a great companion to the Riva Parakeet multilingual ASR streaming model for voice agent use cases.
Benefits
Explore the Benefits of NVIDIA Riva
Multilingual Transcriptions and Expressive Voice Generation
Achieve high multilingual transcription and translation accuracy, and provide out-of-the-box, expressive, professional female and male voices with state-of-the-art models pretrained on thousands of hours of audio.
Fully Customizable
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 brand voice and intonation you want.
Flexible Deployments
Provide consistent experiences to hundreds of thousands of concurrent users with higher inference performance than existing technology, and deploy anywhere—in data centers, on premises, in the cloud, at the edge, or inembedded devices.
Enterprise-Grade AI
Accelerate the development and deployment of production-grade, multilingual, voice-enabled AI applications with NVIDIA Riva, part of theNVIDIA AI Enterprise modular, flexible platform for accelerating AI development and deployment.
NVIDIA Riva NIMs—Now Available for Download
Experience new ASR, TTS and NMT microservices now available—designed to provide optimized AI inference for speech and translation AI. This includes Parakeet models that deliver recording setting ASR accuracy and performance.
Use Cases
How Riva Is Being Used
See how NVIDIA AI supports industry use cases, and jump-start your speech AI development with curated examples.
- AI Virtual Assistant
- Agent Assist
- Digital Human
- Transcription
- AI Translation
- AI Robot
AI Virtual Assistant
Companies are deploying AI virtual assistants to automatically address the queries of millions of customers and employees around the clock. With Riva speech and translation AI microservices, these assistants provide helpful and natural responses at every turn of the conversation despite background noise, poor sound quality, and diverse speaker dialects and accents.
Agent Assist
Consumers expect contact center agents to resolve their issues quickly and efficiently. To meet these expectations and deliver the best customer and agent experiences possible, enterprises across industries are implementing agent-assist technology powered by Riva speech and translation AI.
Digital Human
To enhance customer service experiences and build stronger relationships, businesses are building digital humans with distinctive brand voices with Riva. With Riva, they can create a unique, high-quality, personalized voice with just three seconds of speech data.
Transcription
With hundreds of millions of online meetings held daily, video conferencing has become an indispensable tool for enterprises. With Riva real-time transcription, video conferencing applications achieve impressive accuracy in live captioning and meeting summarizations, accommodating users with worldwide accents and diverse, domain-specific vocabulary.
AI Translation
In the global economy, businesses operate across many countries and serve customers with diverse linguistic and cultural backgrounds. This diversity in global languages poses a unique challenge in finding native speakers or training employees in multiple languages. Riva translation empowers accurate and effective communication, facilitating smooth global interactions.
AI Robot
AI robots are increasingly found in hospitals, airports, and retail stores worldwide. They aid frontline workers by handling daily repetitive tasks in restaurants and manufacturing facilities, assist customers in locating items in stores, and support physicians and nurses in patient care. With Riva, it’s easy to add speech and translation AI to service robots.
Starting Options
Ways to Get Started With NVIDIA Riva
Use the right tools and technologies to build and deploy fully customizable, multilingual speech and translation AI applications.
Try
Experience Riva through a UI-based portal for exploring and prototyping with NVIDIA-managed endpoints, available for free through NVIDIA's API catalog.
Deploy
Get a free license to try NVIDIA AI Enterprise for 90 days using your existing infrastructure.
Experience
Access NVIDIA-hosted infrastructure and guided hands-on labs that include step-by-step instructions and examples, available for free on NVIDIA LaunchPad.
Customer Stories
How Industry Leaders Are Driving Innovation With Riva
Speech AI for Award-Winning Customer Care
Customer: T-Mobile
Products: NVIDIA Riva, NVIDIA-Certified Systems
Technologies: NVIDIA Data Center GPUs, NVIDIA NeMo, NVIDIA Riva
World-Class Speech AI for the Best Video Conferencing Experience
Customer: RingCentral
Products: NVIDIA DGX, NVIDIA Riva
Technologies: NVIDIA Data Center GPUs, NVIDIA NeMo, NVIDIA Riva, NVIDIA Triton Inference Server
Automating Real-Time Arabic Speech Recognition
Customer: Tarteel.ai
Products: NVIDIA Riva, NVIDIA-Certified Systems
Technologies: NVIDIA NeMo, NVIDIA Riva, NVIDIA Data Center GPUs
Adopters
Leading Adopters Across All Industries
- Customers
- Partners
- Service Delivery Partners
Resources
The Latest in NVIDIA Riva Resources
- Blogs
- Sessions
- Training
- Videos
Get Started With Highly Accurate Custom ASR
Learn to build, train, fine-tune, and deploy a GPU-accelerated ASR service with Riva that includes customized features.
Talk to Your Data in Your Native Language
Join AI experts to learn how to build, fine-tune, and deploy production-ready, multilingual speech and translation AI on top of LLM-based applications, enabling your chatbots to speak to your customers in their natural languages.
Try Riva on NVIDIA LaunchPad
Have an existing speech AI project? Apply to get hands-on experience testing and prototyping your conversation-based solutions with speech skills in the high-performance Riva software stack that’s deployable today.
Using Speech AI for Transcription, Translation, and Voice
Build world-class, fully customizable, speech AI applications such as intelligent virtual assistants, audio transcription services, and digital avatars.
Reinvent Contact Center Experiences With NVIDIA Riva
By generating an accurate transcript of customer interactions in real time, Riva enables AI to provide contextual insights, measure sentiment, and recommend the next-best action to an agent, ensuring a great personalized experience.
Robot Dog Fetches Snacks Across Town
Watch as Spot uses speech AI to order snacks across town without an internet connection. Instead of uploading voice commands to the cloud and processing them on the server, Spot processes everything locally for seamless, efficient performance and delivery.
AI2Labs
In 2021, AI2Labs spun off from Yoozoo Games as a local tech startup in Singapore. AI2Labs innovates, experiments, and develops AI products and applications, enabling efficient processes and improving sustainability and business outcomes.
AI2Labs integrated Riva into their Speakr—domain-specific speech AI—speech recognition API to accommodate the intricacies of Asian speech and business domains and achieved state-of-the-art Singlish translation accuracy.
Avaya
Avaya specializes in cloud communications and workstream collaboration solutions, providing unified communications, contact center, communications platform as a service (CPaaS), and services with their OneCloud platform.
Avaya integrated the NVIDIA Riva speech-to-text engine for real-time captions at scale. Riva enables better transcription quality, lower word-error rate, and economical delivery.
C-DAC
For over 10 years, the Applied AI Group at C-DAC in Pune, India, has focused on research and development of speech technology. They’ve successfully created a cutting-edge speech-to-text (STT) system for Indic languages such as Hindiand Marathi. The group continues to advance their work by exploring AI-enabled, open-source deep learning frameworks, libraries, and tools for creating STT and speech-enabled applications for other Indic and low-resource languages. Experiments were conducted using various neural network architectures and topologies from NVIDIA’s open-source NeMo framework, with Citrinet and Conformer-CTC network topologies proving to be effective in building and training neural acoustic models for speech recognition. These models were trained on single- and multi-node Param Siddhi AI systems, optimizing training time and performance. Finally, the models were deployed for real-time and batch-mode inference using the Riva GPU-accelerated production pipeline.
NCS
NCS, a subsidiary of Singtel Group, is a leading technology services firm with presence in Asia Pacific and partners with governments and enterprises to advance communities through technology. Combining the experience and expertise of its 12,000-strong team across 61 specialisations, NCS provides differentiated and end-to-end technology services to clients with its NEXT capabilities in digital, data, cloud and platforms, as well as core offerings in application, infrastructure, engineering and cybersecurity. NCS also believes in building a strong partner ecosystem with leading technology players, research institutions and start-ups to support open innovation and co-creation.
NCS uses NVIDIA Riva TTS in Breeze—the driver’s companion app—for voice-guided navigation, live traffic and road condition updates, real-time parking rates, and electronic road pricing rates and operating hours, to help Singapore drivers experience smooth driving journeys.
Learn more.
RingCentral
RingCentral, a leading provider of global enterprise cloud communications, collaboration, and contact center solutions, serves millions of users. The RingCentral platform empowers collaboration from any location and device, improving business efficiency and customer satisfaction. RingCentral uses NVIDIA Riva for video conferencing transcription for 200,000 concurrent users on their platform.
Learn more.
Snap
Snap is a camera and social media company that enables multimedia message creation with filters and effects. To create more interactive experiences, Snapchat users play with Lenses—a feature that adds real-time effects into snaps—over 6 billion times per day.
NVIDIA Riva’s noise- and lingo-optimized speech AI service is integrated into Snap AR Lens Studio, enabling creators—artists and developers—to build gripping augmented reality (AR) experiences.
T-Mobile
T-Mobile, a supercharged Un-carrier, delivers an advanced 4G LTE and transformative 5G network for the best customer experience. To empower contact center agents, T-Mobile implements Expert Assist. This AI-based software uses NVIDIA Riva to transcribe real-time customer conversations that feed recommenders and assist thousands of agents.
With Riva, T-Mobile fine-tunes automatic speech recognition models on custom datasets and interprets customer jargon accurately across noisy environments.
Learn more.
Building Speech AI Applications
Explore how to get started with integrating and deploying Riva ASR and TTS models in production with high-performance inference and minimal effort.
An Introduction to NVIDIA Riva
Learn about Riva’s architecture, key features, and components for building speech and translation AI services.
NVIDIA Parlays Win in Voice Challenge
Read how a team of NVIDIANs won the LIMMITS ’24 challenge, which asked contestants to recreate in real time a speaker’s voice in English or any of six languages spoken in India with the appropriate accent.
Next Steps
Ready to Get Started?
Use the right tools and technologies to build and deploy fully customizable, multilingual, speech and translation AI applications.
For Developers
Explore everything you need to start developing with NVIDIA Riva, including the latest documentation, tutorials, technical blogs, and more.
Get in Touch
Talk to an NVIDIA product specialist about moving from pilot to production with the security, API stability, and support ofNVIDIA AI Enterprise.
- NVIDIA AI Enterprise Platform
- Agentic AI - Agent Intelligence Toolkit
- AI Blueprints
- AI Foundry
- AI Foundation Models
- AI Inference - Dynamo
- AI Inference Microservices - NIM
- AI Microservices - CUDA-X
- Avatar - Tokkio
- Cybersecurity - Morpheus
- Data Science - RAPIDS
- Data Science - Apache Spark
- Decision Optimization - cuOpt
- Generative AI - NeMo
- Physical AI - Cosmos
- Speech AI - Riva