Skip to main content
ContainersNVIDIADeepSeek-R1NVIDIALlama-3.1-Nemotron-70B-InstructNVIDIAPyTorch
CollectionsNVIDIAOmniverse Kit (FB)NVIDIADeepStream SDKNVIDIAOmniverse Kit App Streaming
ModelsNVIDIAStyleGAN3 pretrained modelsNVIDIAPeopleNetNVIDIATrafficCamNet
ResourcesNVIDIARiva Skills Quick Start
Helm ChartsNVIDIAGPU OperatorNVIDIANVIDIA NIM Operator
  • SearchSearch thousands of GPU-optimized Containers, pretrained Models, SDKs, and Helm charts—ready to accelerate AI, digital twins, and HPC from cloud to edge.
    NVIDIA AI Enterprise
    NVIDIA AI Enterprise
    3
    3
    1
    1
  • NVIDIA NIM
    NVIDIA NIM
    4
  • NIM Container GPUs
    NIM Container GPUs
  • Use Case
    Use Case
    119
    105
    65
    60
    38
    37
    35
    34
    33
    33
    27
    26
    24
    24
    22
    21
    14
    13
    12
    11
    10
    10
    9
    8
    8
    5
    4
    4
    3
    2
    1
    1
    1
    1
    1
    1
  • NVIDIA Platform
    NVIDIA Platform
    6
    5
    3
    2
    1
    1
    1
    1
    1
    1
  • Industry
    Industry
    2
    1
  • Solution
    Solution
    13
    5
    4
    3
    2
    1
    1
  • Publisher
    Publisher
    16
    8
  • Policy
    Policy
  • Displaying 27 results
    Riva Speech Skills
    NVIDIA
    Riva Speech Skills is a scalable Conversational AI service platform.
    Container
    Riva TTS NIM
    NVIDIA
    RIVA TTS NIM provide easy access to state-of-the-art text to speech models, capable of synthesizing English speech from text
    Container
    Riva Skills Quick Start
    NVIDIA
    Scripts and utilities for getting started with Riva Speech Skills
    Resource
    TTS FastPitch HifiGAN Riva
    NVIDIA
    RIVA TTS NIM provide easy access to state-of-the-art text to speech models, capable of synthesizing English speech from text
    Container
    Chatterbox TTS Multilingual
    Nvidia
    Chatterbox TTS Multilingual NIM Container
    Container
    Magpie TTS Zeroshot NIM
    NVIDIA
    Riva Magpie TTS Zeroshot NIM synthesizes natural sounding speech using voice features from reference speech sample.
    Container
    WaveGlow LJS 256 Channels
    NVIDIA
    WaveGlow model weights pre-trained on the LJ Speech dataset to be used with https://github.com/NVIDIA/waveglow.
    Model
    HiFi-GAN PyT checkpoint (22kHz, AMP)
    NVIDIA Deep Learning Examples
    HiFi-GAN v1 PyTorch checkpoint trained on 8GPU with AMP on LJSpeech-1.1 (22kHz).
    Model
    WaveGlow
    NVIDIA
    WaveGlow is a flow-based network capable of generating high quality speech from mel-spectrograms.
    Model
    Text to Speech Notebook
    NVIDIA
    End to End workflow for text to speech training with TAO Toolkit and deployment using Riva.
    Resource
    HiFi-GAN PyT checkpoint (FastPitch ftune, 22kHz, AMP)
    NVIDIA Deep Learning Examples
    HiFi-GAN v1 PyTorch checkpoint trained on 8GPU with AMP on LJSpeech-1.1 (22kHz), fine-tuned on FastPitch outputs.
    Model
    Tacotron2 LJSpeech
    NVIDIA
    Model checkpoints for the Tacotron 2 model trained with NeMo.
    Model
    Audio Codec 16kHz Small
    NVIDIA
    This model card contains a Small Audio Codec model trained on the Libri-Light audiobook recordings dataset, comprising approximately 60,000 hours of English language speech with a 16kHz sampling rate.
    Model
    WaveGlow LJSpeech
    NVIDIA
    Model checkpoints for the WaveGlow model trained with NeMo.
    Model
    HiFi-GAN for PyTorch
    NVIDIA Deep Learning Examples
    HiFi-GAN model implements a spectrogram inversion model that allows to synthesize speech waveforms from mel-spectrograms.
    Resource
    RIVA Magpie-TTS Multilingual
    NVIDIA
    Riva NeMo-MagpieTTS Multilingual IPA multispeaker model with Emotions
    Model
    Tacotron2 PyTorch checkpoint (AMP)
    NVIDIA Deep Learning Examples
    Tacotron2 PyTorch checkpoint trained with AMP
    Model
    Flowtron
    NVIDIA
    Flowtron is an Autoregressive Flow-based Network for Text-to-Mel-spectrogram Synthesis.
    Model
    Tacotron2 and Waveglow 2.0 for PyTorch
    NVIDIA Deep Learning Examples
    The Tacotron 2 and WaveGlow model form a text-to-speech system that enables user to synthesise a natural sounding speech from raw transcripts.
    Resource
    FastPitch checkpoint (PyTorch, AMP, LJSpeech-1.1, 22050Hz)
    NVIDIA Deep Learning Examples
    FastPitch PyTorch checkpoint trained on LJSpeech-1.1
    Model
    Mel Codec 22kHz fullband medium
    —
    22.05kHz full-band Mel Codec model trained on multi-lingual speech.
    Model
    OpenVoice
    —
    A collection of models to enable OpenVoice support for the NVIDIA In-Game Inferencing (NVIGI) SDK.
    Model
    FastPitch 1.0 for PyTorch
    NVIDIA Deep Learning Examples
    The FastPitch model generates mel-spectrograms from raw input text and allows to exert additional control over the synthesized utterances.
    Resource
    Waveglow PyTorch checkpoint
    NVIDIA Deep Learning Examples
    Waveglow PyTorch checkpoint trained with AMP
    Model

    NVIDIA uses cookies to improve your experience on our web site. We and our third-party partners also use cookies and other tools to collect and record information you provide as well as information about your interactions with our websites for performance improvement, analytics, and to assist in marketing efforts. By clicking "Accept All", you consent to our use of cookies and other tools as described in our Cookie Policy. You can manage your cookie settings by clicking on "Manage Settings." By continuing to use this site or by clicking one of the buttons below, you agree to our Terms of Service (which contains important waivers). Please see our Privacy Policy for more information on our privacy practices.