Qwen3-Omni

Trace how the Qwen3-Omni line moved from audio-visual chat to agent execution: separate offline and realtime APIs, very long audio and video inputs, and reasoning wired into tool calls.

Qwen3-Omni is Qwen's omni-modal line, and three releases trace its course. The December 2025 Flash update smoothed multi-turn video and audio chat across realtime and offline APIs and covered 119 text languages. Qwen3.5-Omni split the family into Plus, Flash and Light, adding long audio input and 113 speech-recognition languages. Qwen3.8-Omni-Flash turns toward agent work: a million-token context, function calling and web search.

Qwen 3.8-Omni-Flash released: Full-modal AI begins directly executing audio and video tasks

Qwen released Qwen 3.8-Omni-Flash , defining it as the first full-modal model built around agent capabilities. It not only handles text, images, audio...

Admin 9/18/2026

Qwen3.5-Omni released: From long-term audio and video understanding to real-time voice and video interaction

Qwen3.5-Omni has been officially released by Qwen. Qwen Chat's experience portal has pointed to VoiceChat and VideoChat. It presses the listening, rea...

Admin 3/31/2026

196

Qwen3-Omni-Flash Releases 2025-12-01 Upgrade Multimodal Sessions are fully enhanced

Alibaba Cloud Tongyi Qianwen team has launched Qwen3-Omni-Flash 2025-12-01 version, which has significantly upgraded video and audio dialogue, voice i...

Admin 12/10/2025

354