Bigvgan_v2_22khz_80band_256x
NVIDIA's BigVGAN is a universal neural vocoder for audio processing and text-to-speech tasks, with a custom CUDA kernel for accelerated inference speed, showing 1.5-3x faster speed on a single A100 GPU. It is trained on large-scale datasets containing diverse audio types, including speech in multiple languages, environmental sounds, and instruments, and supports up to 44 kHz sampling rate and 512x upsampling ratio. BigVGAN's architecture is notable for its multi-scale sub-band CQT discriminator and multi-scale mel spectrogram loss, which contribute to its capabilities.
Input
Output
Context
-
Max Output
-
Parameters
-
Technical Specifications
Input Modalities
Output Modalities
Capabilities
Loading capabilities…
Resources & Links
More models by NVIDIA
The creator's other models in the catalog, with their context, size and license where published.
Compare it, or keep browsing
Put this model beside its alternatives on the same evidence, or go back to the full catalog.
Frequently asked questions about Bigvgan_v2_22khz_80band_256x
Answered from the entry's own fields: context, license, modalities, evidence, serving and the memory to self-host.
NVIDIA has not published a context window for Bigvgan_v2_22khz_80band_256x, so the catalog shows it as not available rather than estimating one.
Yes. Bigvgan_v2_22khz_80band_256x is an open-weight model released under the MIT license, so the weights can be downloaded and self-hosted within that license's terms.
Bigvgan_v2_22khz_80band_256x accepts Audio and produces Audio. The capabilities card on this page lists which API features each deployment honours, such as function calling and structured output, with the source each was checked against.
No published benchmark result for Bigvgan_v2_22khz_80band_256x is in the catalog yet, so the model is shown as unmeasured. It is not ranked or estimated; the router treats it as unknown for every task until a suite measures it.
Not on the managed pool today; Bigvgan_v2_22khz_80band_256x is listed for reference and comparison. Connect your own provider key or endpoint that serves it and the gateway runs it on your account, with routing decisions recorded the same way.
NVIDIA has not published a parameter count for Bigvgan_v2_22khz_80band_256x, so the catalog cannot estimate its memory footprint. The capacity planner can size it from a parameter count you supply.
Fields collected from public registries, host APIs and benchmark publishers, each tagged with its source.
Last updated: Aug 28, 2026
Put intelligence in the middle.
One gateway in front of every model, with your policies applied and every decision on record. Start with $5 of credit and 5,000 routing decisions a month, no card required.