NVIDIA Buildmodels.m31a
Models Directory/nvidia/Studio Voice
nvidiaCatalog Onlyfree endpoint

Studio Voice

nvidia/studiovoice
NVIDIA Build Card

Enhance input speech recorded with low-quality microphones in noisy or reverberant environments, producing studio-quality speech.

Context Length
Not published
Input Pricing
Not published
Output Pricing
Not published
Recent Latency
No probes

Model Architecture & Limits

Canonical IDnvidia/studiovoice
Publisher / Originatornvidia
Model FamilyNot published
ArchitectureConvolution Neural Networks (CNNs), Transformers, Generative Adversarial Networks (GANs) (Encoder-Decoder)
Context Window LimitNot published
Max Output TokensNot published
Endpoint Protocolnim-custom

Capabilities & Modal Surfaces

Chat Conversation✕ No
Tool / Function Calling✕ No
Reasoning / Thinking✕ No
Structured Output (JSON)✕ No
Vision / Multimodal✕ No
Audio Processing✓ Yes
License & Restrictions
Use of this model is governed by the [NVIDIA Open Model License](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/).
Commercial and research use permitted under governing model and API terms.