Qwen3-Omni
lastmod 2025-12-14created 2025-12-141 edits
Qwen3-omni is a natively end-to-end, omni-modal LLM developed by the Qwen team at Alibaba Cloud, capable of understanding text, audio, images, and video, as well as generating speech in real time.
Qwen3-Omni-Flash-2025-12-01
Qwen3-Omni-Flash-2025-12-01 is a next-generation multimodal model that processes text, images, audio and video at the same time and generates text and speech output via real-time streaming
- Greatly improved understanding of audio-visual instructions and conversational stability, enabling natural and consistent audio-video interaction
- Full control over the system prompt allows fine-grained adjustment of persona style, tone, output length and more
- Supports text in 119 languages, speech recognition in 19 languages and speech synthesis in 10 languages, solving multilingual consistency issues
- Improved performance across all areas, including logical reasoning, code generation and visual/audio understanding, providing a natural and precise AI interaction experience