Can't speak to OWUI (llama.cpp's built in web UI has been sufficient for me), but for image generation, you'll need to grab a different piece of software to handle that as Ollama only does LLMs, not diffusion models. The two main options for that are ComfyUI and Automatic1111, though I will warn that both require far more manual setup than Ollama does.

- Opinion warning -

I would highly recommend you move away from Ollama and switch to llama.cpp or ik_llama.cpp if you can. While Ollama is by far the simplest, most plug-and-play solution, it has a handful odd or misleading design choices that make doing anything worthwhile kind of annoying, like setting the context size to 4096 (are we in 2023 or something?) by default a weird, nonstandard model naming scheme. Ollama configuration is also painfully limited, while llama.cpp exposes a lot more knobs and dials you can tune to get the best performance you can.

Additionally, you may want to swap out some of the models you're using for newer ones. As it is unlikely you are running the full 685B parameter Deepseek-R1 on your home rig since it requires >500 GB of RAM to run at any appreciable speed, you're probably running one of the "distills," which are smaller models that were fine-tuned to behave like the full-sized model. The Deepseek distills, along with every Llama model, are practically ancient by LLM standards and have since been far outclassed by newer models that are around the same size or even smaller. If you want somewhere to start, check out the new Qwen3.5 models.

Audio transcribing should be the little "waveform" icon at the right of the text input:

Image generation, I'm not sure as that's not a use-case I have and don't think the small-ish models I run are even capable of that.

I'm not sure how audio transcribing works in OpenWebUI (I think it has built-in models for that?) but image generation is a "capability" that needs to be both part of the model and enabled in the models settings (Admin => Settings => Models)