Qwen3-Omni
Qwen3-Omni is a natively end-to-end multilingual omni-modal foundation model that processes text, images, audio, and video and delivers real-time streaming responses in text and natural speech. It uses a Thinker-Talker architecture with a Mixture-of-Experts (MoE) design, early text-first pretraining, and mixed multimodal training to support strong performance across all modalities without sacrificing text or image quality. The model supports 119 text languages, 19 speech input languages, and 10 speech output languages. It achieves state-of-the-art results: across 36 audio and audio-visual benchmarks, it hits open-source SOTA on 32 and overall SOTA on 22, outperforming or matching strong closed-source models such as Gemini-2.5 Pro and GPT-4o. To reduce latency, especially in audio/video streaming, Talker predicts discrete speech codecs via a multi-codebook scheme and replaces heavier diffusion approaches.
Learn more
HunyuanOCR
Tencent Hunyuan is a large-scale, multimodal AI model family developed by Tencent that spans text, image, video, and 3D modalities, designed for general-purpose AI tasks like content generation, visual reasoning, and business automation. Its model lineup includes variants optimized for natural language understanding, multimodal vision-language comprehension (e.g., image & video understanding), text-to-image creation, video generation, and 3D content generation. Hunyuan models leverage a mixture-of-experts architecture and other innovations (like hybrid “mamba-transformer” designs) to deliver strong performance on reasoning, long-context understanding, cross-modal tasks, and efficient inference. For example, the vision-language model Hunyuan-Vision-1.5 supports “thinking-on-image”, enabling deep multimodal understanding and reasoning on images, video frames, diagrams, or spatial data.
Learn more
HunyuanVideo-Avatar
HunyuanVideo‑Avatar supports animating any input avatar images to high‑dynamic, emotion‑controllable videos using simple audio conditions. It is a multimodal diffusion transformer (MM‑DiT)‑based model capable of generating dynamic, emotion‑controllable, multi‑character dialogue videos. It accepts multi‑style avatar inputs, photorealistic, cartoon, 3D‑rendered, anthropomorphic, at arbitrary scales from portrait to full body. Provides a character image injection module that ensures strong character consistency while enabling dynamic motion; an Audio Emotion Module (AEM) that extracts emotional cues from a reference image to enable fine‑grained emotion control over generated video; and a Face‑Aware Audio Adapter (FAA) that isolates audio influence to specific face regions via latent‑level masking, supporting independent audio‑driven animation in multi‑character scenarios.
Learn more
Qwen3-VL
Qwen3-VL is the newest vision-language model in the Qwen family (by Alibaba Cloud), designed to fuse powerful text understanding/generation with advanced visual and video comprehension into one unified multimodal model. It accepts inputs in mixed modalities, text, images, and video, and handles long, interleaved contexts natively (up to 256 K tokens, with extensibility beyond). Qwen3-VL delivers major advances in spatial reasoning, visual perception, and multimodal reasoning; the model architecture incorporates several innovations such as Interleaved-MRoPE (for robust spatio-temporal positional encoding), DeepStack (to leverage multi-level features from its Vision Transformer backbone for refined image-text alignment), and text–timestamp alignment (for precise reasoning over video content and temporal events). These upgrades enable Qwen3-VL to interpret complex scenes, follow dynamic video sequences, read and reason about visual layouts.
Learn more
