Qwen3-Omni: Native Omni AI model for text, image and video

Re:Qwen3-Omni: Native Omni AI model for text, image and video by simonw on Monday September 22, 2025 @03:58PM (#45338682)

You can try it out on https://chat.qwen.ai/ - sign in with Google or GitHub (signed out users can't use the voice mode) and then click on the voice icon.

It has an entertaining selection of different voices, including:

*Dylan* - A teenager who grew up in Beijing's hutongs

*Peter* - Tianjin crosstalk, professionally supporting others

*Cherry* - A sunny, positive, friendly, and natural young lady

*Ethan* - A sunny, warm, energetic, and vigorous boy

*Eric* - A Sichuan Chengdu man who stands out from the crowd

*Jada* - The fiery older sister from Shanghai

[ Parent | on HN ]

Re:Qwen3-Omni: Native Omni AI model for text, image and video by indigodaddy on Monday September 22, 2025 @04:13PM (#45338859)

I only see Omni Flash, is that the one?

[ Parent | on HN ]

Re:Qwen3-Omni: Native Omni AI model for text, image and video by furiousteabag on Monday September 22, 2025 @05:31PM (#45339739)

same, did you figure it out?

[ Parent | on HN ]

Re:Qwen3-Omni: Native Omni AI model for text, image and video by simonw on Monday September 22, 2025 @06:04PM (#45340157)

I think so, you need to click the big jagged audio icon to start a voice session.

[ Parent | on HN ]

Re:Qwen3-Omni: Native Omni AI model for text, image and video by karimf on Monday September 22, 2025 @11:35PM (#45342576)

Is the Qwen3-Omni-Flash the same as Qwen3-Omni-30B-A3B, or is the Omni-Flash a different closed-source model?

[ Parent | on HN ]

Re:Qwen3-Omni: Native Omni AI model for text, image and video by fivestones on Wednesday September 24, 2025 @03:15PM (#45364773)

My question too

[ Parent | on HN ]

Re:Qwen3-Omni: Native Omni AI model for text, image and video by ltdemey on Thursday September 25, 2025 @10:23AM (#45372968)

In Section 5 of their [technical report](https://arxiv.org/pdf/2509.17765v1) they mention them

"... A comprehensive evaluation was performed on a suite of models, including Qwen3-Omni-30B-A3B- Instruct, Qwen3-Omni-30B-A3B-Thinking, and two in-house developed variants, designated Qwen3- Omni-Flash-Instruct and Qwen3-Omni-Flash-Thinking. These “Flash” models were designed to improve both computational efficiency and performance efficacy, integrating new functionalities, notably the support for various dialects. ..."

[ Parent | on HN ]

Re:Qwen3-Omni: Native Omni AI model for text, image and video by flockonus on Monday September 22, 2025 @04:32PM (#45339057)

The voices are really fun, thanks for the laughs :)

[ Parent | on HN ]

Re:Qwen3-Omni: Native Omni AI model for text, image and video by vladgur on Monday September 22, 2025 @07:31PM (#45340926)

Many of these voices are especially hillarious when you switch the language.

In Russian, Ryan sounds like a westerner who started reading Russian words a month ago.

Dylan sounds somewhat authentic, while everyone else is a different degree of heavy-asian-accented Russian.

[ Parent | on HN ]