# Baidu Releases NAVA for Text-to-Video with Audio

> The new model from the Chinese tech giant uses a Multimodal Diffusion Transformer to generate synchronized audio and video from text or image prompts.

Published by The Open Weights on May 29, 2026. Canonical: https://theopenweights.com/news/nava-xei6

## Key facts

- Company: Baidu
- Model: NAVA
- Version: 1
- Category: Text → Video
- Modalities: Text → Video
- License: Other (Open weights, commercial use allowed)
- Architecture: ti2v
- Resolution: 1280×704
- Languages: English, Chinese
- Significance: notable
- Published: 2026-05-29
- Last verified: 2026-06-17
- Hugging Face: https://huggingface.co/baidu/NAVA
- Canonical URL: https://theopenweights.com/news/nava-xei6

Baidu has released the weights for NAVA, a new generative model capable of producing video complete with synchronized audio from a variety of inputs. NAVA, which stands for Native Audio-Video Animation, can take either a text prompt or a combination of text and an image to generate short video clips. The model and examples are available on its [Hugging Face repository](https://huggingface.co/baidu/NAVA).

Under the hood, NAVA employs a sophisticated architecture known as a Multimodal Diffusion Transformer (MMDiT). This design allows the model to process and integrate different data types—like text and image features—within the same transformer blocks, creating a more cohesive understanding of the prompt. The model is built upon Baidu's own Wan2.2 video foundation model, extending its capabilities into multimodal generation.

## A More Efficient Method

Instead of traditional diffusion methods, NAVA is trained using a flow-matching technique. This is a more recent approach to training generative models that can lead to more efficient training and faster inference times, as it learns the direct path from noise to a final, coherent output. This choice of technique points to a growing trend toward more computationally efficient generative architectures.

The release of NAVA adds another significant open-weights model to the competitive text-to-video landscape. Its ability to generate audio natively alongside video is a key differentiator, as audio is often a separate, post-processing step for other models. While the model is publicly available, it uses a custom license, so developers and researchers should review the terms before incorporating it into their work.

## Get the model

- [Hugging Face](https://huggingface.co/baidu/NAVA)

## Sources

- [baidu/NAVA](https://huggingface.co/baidu/NAVA) — Hugging Face, May 29, 2026

---
Source: The Open Weights (https://theopenweights.com/). Aggregated and written by Claude, curated by humans. Cite as: "Baidu Releases NAVA for Text-to-Video with Audio", The Open Weights, May 29, 2026, https://theopenweights.com/news/nava-xei6