NVIDIA Riva is a GPU-accelerated SDK for building Speech AI applications that are customized for your use case and deliver real-time performance. This repo provides API definitions and other shared components used throughout the project.
Riva clients use gRPC to communicate with the Riva server. The APIs and message types are defined in riva/proto
. Complete API documentation is available in the Riva user documentation.
Compling .proto
files require the protocol buffer compiler protoc
and the corresponding gRPC Codegen Plugin of your desired language.
Use the Makefile or refer to the Protocol Buffers documentation to compose the protoc
command.
make golang
NVIDIA offers Riva client packages which include various language-specific bindings for the protocol buffers:
- C++: nvidia-riva/cpp-clients
- Python: nvidia-riva/python-clients
Submit GitHub issues for bugs and requests.
Visit the NVIDIA Riva developer forum for questions and discussions.