NVIDIA Riva support for Jetson Orin Nano with JetPack 7.2

Hello, NVIDIA community.

I have a Jetson Orin Nano Super Developer Kit and recently upgraded it to JetPack 7.2.

I am trying to use NVIDIA Riva to develop a voice agent application (ASR + TTS), but I have encountered a limitation: at the moment, the available Riva version in the Quickstart appears to be targeted at the Jetson Thor platform, and I have not found compatible support/models for my environment running Jetson Orin Nano + JetPack 7.2.

I would like to know:

  • Is there any roadmap or estimated timeline for making NVIDIA Riva available for Jetson Orin Nano with JetPack 7.2?

  • Will the Jetson Orin platform continue to be supported in future Riva releases?

  • As an alternative, would it make sense to downgrade to JetPack 6.2 in order to use a current Riva version that is compatible with Orin?

My goal is to use the Jetson Orin Nano as an edge AI device for an embedded voice agent, taking advantage of GPU acceleration, TensorRT, and the capabilities of the Jetson platform.

My configuration:

  • Hardware: NVIDIA Jetson Orin Nano Super Developer Kit
  • Arch: ARM64 (aarch64)
  • JetPack: 7.2
  • L4T: R39.2
  • CUDA Toolkit: 13.2 (nvcc 13.2.78)
  • TensorRT: 10.16.2.10 + CUDA 13.2
  • Docker NVIDIA Runtime: configured and working

Thank you for your support!

Hello @albertogranja!

Based on the title and content of your topic, it looks like it may receive better visibility and feedback in a different category. We took the liberty of moving it for you.

If this was an incorrect assessment, please send me a direct message.

Disclaimer: this moderation suggestion and message were generated with AI assistance.

Hi,

We need to check with our internal team.
Will get back to you later.

Thanks.

Hi,

Thanks for your patience.

We have a new inference solution now, which has been verified on Jetpack 7.2+Orin.

nemo-speech.cpp | NVIDIA NGC

Instructions and steps to get started are on the NGC overview page.

Thanks.