# NVIDIA Riva

> A GPU-accelerated SDK for building Speech AI applications with real-time performance

NVIDIA Riva is a toolkit for production-grade conversational AI inference, offering fully customizable speech models with state-of-the-art accuracy and leading performance. It provides pretrained models for speech recognition, speech synthesis, natural language processing, and translation that can be fine-tuned on domain-specific data.

## Docs

- [Quick Start Guide](https://docs.nvidia.com/deeplearning/riva/user-guide/docs/quick-start-guide.html): Deploy Riva on your local workstation and run sample clients
- [Overview](https://docs.nvidia.com/deeplearning/riva/user-guide/docs/overview.html): Learn about Riva's capabilities and architecture
- [Installation](https://docs.nvidia.com/deeplearning/riva/user-guide/docs/installation/deploy-local.html): Deploy Riva locally with Docker or on Kubernetes
- [Support Matrix](https://docs.nvidia.com/deeplearning/riva/user-guide/docs/support-matrix/support-matrix.html): Hardware, software, and model compatibility information

## Core Components

- [Speech Recognition (ASR)](https://docs.nvidia.com/deeplearning/riva/user-guide/docs/asr/asr-overview.html): Real-time and batch speech transcription with customization options
- [Speech Synthesis (TTS)](https://docs.nvidia.com/deeplearning/riva/user-guide/docs/tts/tts-overview.html): Human-like speech generation with SSML support and custom voice creation
- [Natural Language Processing (NLP)](https://docs.nvidia.com/deeplearning/riva/user-guide/docs/nlp/nlp-overview.html): Punctuation, capitalization, and text processing capabilities
- [Translation (NMT)](https://docs.nvidia.com/deeplearning/riva/user-guide/docs/translation/translation-overview.html): Text and speech translation across multiple languages

## Tutorials

- [ASR Tutorials](https://docs.nvidia.com/deeplearning/riva/user-guide/docs/tutorials-asr-contents.html): Fine-tune and deploy custom speech recognition models
- [TTS Tutorials](https://docs.nvidia.com/deeplearning/riva/user-guide/docs/tutorials-tts-contents.html): Create custom voices and improve speech synthesis quality
- [NMT Tutorials](https://docs.nvidia.com/deeplearning/riva/user-guide/docs/tutorials-nmt-contents.html): Deploy and fine-tune translation models
- [Cloud Deployment](https://docs.nvidia.com/deeplearning/riva/user-guide/docs/tutorials-deploy-contents.html): Deploy Riva at scale on AWS, Azure, Google Cloud and Oracle Cloud

## Development

- [Model Customization](https://docs.nvidia.com/deeplearning/riva/user-guide/docs/model-overview.html): Fine-tune and deploy custom models with NVIDIA NeMo
- [Python API](https://docs.nvidia.com/deeplearning/riva/user-guide/docs/apis/development-python.html): Integrate Riva services into Python applications
- [Command-line Tools](https://docs.nvidia.com/deeplearning/riva/user-guide/docs/apis/cli.html): Interact with Riva services through CLI tools
- [Sample Applications](https://docs.nvidia.com/deeplearning/riva/user-guide/docs/samples/index.html): Example applications showcasing Riva capabilities

## Optional

- [Reference Documentation](https://docs.nvidia.com/deeplearning/riva/user-guide/docs/reference/models/index.html): Detailed model specifications and protocol definitions
- [Troubleshooting](https://docs.nvidia.com/deeplearning/riva/user-guide/docs/troubleshooting.html): Common issues and solutions
- [Release Notes](https://docs.nvidia.com/deeplearning/riva/user-guide/docs/release-notes.html): Latest updates and changes
- [Developer Forum](https://forums.developer.nvidia.com/c/ai-data-science/deep-learning/riva/475): Community support and discussions