LavaSR

What is this model? BigVGAN‑v2 22kHz 80‑Band 256× is a high‑fidelity neural vocoder that converts mel‑spectrograms into waveforms.

What is this model? nvidia/bigvgan_v2_44khz_128band_512x is a high‑fidelity universal neural vocoder that converts mel‑spectrograms into waveform audio at a 44 kHz sampling rate.

Key Features & Capabilities End‑to‑end speech conversion: Handles speech‑to‑speech, speech‑to‑text‑to‑speech, and voice‑style transfer without intermediate text.