[New Model]: Step-Audio-R1.1

[fake0fan]

The model to consider.

https://huggingface.co/stepfun-ai/Step-Audio-R1.1

The closest model vllm-omni already supports.

No response

What's your difficulty of supporting the model you want?

No response

Use case and motivation

Step-Audio R1.1 (Realtime) is a major upgrade to Step-Audio-R1, designed for interactive spoken dialogue with both real-time responsiveness and strong reasoning capability.

Unlike conventional streaming speech models that trade intelligence for latency, R1.1 enables thinking while speaking, achieving high intelligence without sacrificing speed.

Before submitting a new issue...

• Make sure you already searched for relevant issues, and asked the chatbot living at the bottom right corner of the documentation page, which can answer lots of frequently asked questions.

[hsliuustc0106]

is this audio output as well?

[fake0fan]

is this audio output as well?

Sure.

[nussejzz]

I'd like to try, can you assign it to me? @hsliuustc0106

[divyanshsinghvi]

@nussejzz are you working on it? If not I can take it up?

[nussejzz]

@divyanshsinghvi Yes, I am

[wtomin]

@nussejzz Hello, I am working on the document of adding a diffusion model to vLLM-Omni. While you are adding this new model, please leave your comments in #1196 . Thanks.