OmniVinci
by NVlabs · GitHub
OmniVinci is an omni-modal LLM for joint understanding of vision, audio, and language.
⭐ Stars
674
🍴 Forks
53
📜 License
Apache-2.0
Commercial use OK📅 Created
2025
🔄 Last commit
4 mo ago
🏷️ Category
audio-language-model
💻 Language
You maintain this project?
Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.
📈 Star history
2026-07-202026-07-21
📄 About
OmniVinci is an omni-modal LLM for joint understanding of vision, audio, and language.
❓ Frequently asked questions
What is OmniVinci?
OmniVinci is an omni-modal LLM for joint understanding of vision, audio, and language.
Is OmniVinci open source?
OmniVinci is an open-source project. It is released under the Apache-2.0 license.
Is OmniVinci free?
Yes. OmniVinci is free and open source — you can use, modify and self-host it.
🏅 Maintainer of this project?
Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.
[](https://opensourceai.tech/project/nvlabs-omnivinci.html)
🧬 Related projects🧬 View the DNA map →
Fun-ASR
Open-source LLM-based ASR model family for Chinese, dialect, accent, and multilingual speech, w…
★ 1.4k · 31-languages
SoundMind
We introduce the Audio Logical Reasoning (ALR) dataset, consisting of 6,446 text-audio annotate…
★ 1.1k · audio-language-model
tensorflow
An Open Source Machine Learning Framework for Everyone
★ 196k · deep-learning