NVIDIA Studio Voice ST 2110 NIM is a real-time AI service that enhances input speech captured through low-quality microphones in noisy and reverberant environments, producing clean, studio-quality audio.
NVIDIA Studio Voice ST 2110 NIM
What Is NVIDIA NIM?
NVIDIA NIM™, part of NVIDIA AI Enterprise, packages AI inferencing services that integrate directly into live SMPTE ST 2110 IP broadcast pipelines. Each NIM is deployed via Helm on a Holoscan for Media cluster and provides reliable, GPU-accelerated inference within production media workflows.
NVIDIA Studio Voice SMPTE ST 2110 NIM is designed for real-time speech enhancement in live IP broadcast environments. The service enhances input speech recorded through low-quality microphones in noisy and reverberant environments to studio-recorded quality speech. The NIM operates on uncompressed SMPTE ST 2110 audio and supports 48 kHz audio for ST 2110 based media pipelines.
Each NIM consists of a container and a model and uses a CUDA-accelerated runtime for NVIDIA GPUs. NIM on Holoscan for Media is the fastest path to integrating AI into live IP broadcast pipelines at production scale.
Getting Started with NVIDIA NIM
Deploying and integrating NVIDIA NIM is straightforward thanks to our industry standard APIs. Visit the NVIDIA Studio Voice ST 2110 NIM page for release documentation, deployment guides and more.
Get Help
Enterprise Support
Get access to knowledge base articles and support cases or submit a ticket.
Governing Terms
Use of the NIM container is governed by the NVIDIA Software License Agreement and the Product-Specific Terms for NVIDIA AI Products. Use of the models is governed by the NVIDIA Open Model License.
You are responsible for ensuring that your use of NVIDIA AI Foundation Models complies with all applicable laws.