QwenLM/Qwen3-Omni

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

3980 stars · 289 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

Qwen3-Omni is a natively end-to-end omni-modal large language model from Alibaba Cloud's Qwen team that understands text, images, audio, and video and generates real-time streaming text and speech responses. The repository provides model weights, Transformers and vLLM usage code, cookbooks, and demos for running the model.

Use cases

• build a voice assistant that listens and talks back in real time
• analyze video content and ask questions about it
• transcribe and understand multilingual audio input
• generate natural speech output from an LLM
• run multimodal chat with images, audio, and video inputs
• serve an omni-modal model with vLLM

When to choose

• you need a single model handling text, audio, image, and video input with speech output
• you want real-time streaming speech responses from an open-weight LLM
• you need multilingual omni-modal understanding with Apache-2.0 licensing

When to avoid

• you only need text-only chat and want a smaller, cheaper model
• you lack GPU resources for large multimodal inference
• you need fine-grained control over separate ASR and TTS pipelines

Facets

library · maturity active

llm-inference speech-recognition tts machine-learning nlp audio-processing video-processing image-processing large-language-models artificial-intelligence speech-processing computer-vision python cross-platform omni-modal multimodal-llm qwen alibaba-cloud speech-generation video-understanding transformers vllm foundation-model natural-language-processing audio gpu linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="QwenLM/Qwen3-Omni")