feat: support mistral.ai image and speech generation through the chat completion endpoint

Which version of integration_openai are you using?

3.10.0

Which version of Nextcloud are you using?

32.0.5

Which browser are you using? In case you are using the phone App, specify the Android or iOS version and device please.

Firefox 147.01

Describe the Bug

Hello one and all!

Just playing around with mistral.ai and nextcloud. I noticed image generation and more important to me text2speech is not working currently with openai integration. Well, it's called "openai" - integration, right, so not a big of a surprise things aren't working.

Question: Is there a solution in the works? I mean, common, mistral is EU stuff and openai isn't. My guess would be nextcloud is prefering the EU variant. :)

Cheers! t.

 RuntimeException OpenAI/LocalAI's text to image generation failed with: API request error: Client error: `POST https://api.mistral.ai/v1/audio/speech` resulted in a `404 Not Found` response: { "message":"no Route matched with those values", "request_id":"c63c8d530a0d5807dcd878405de5c70e" } 

Expected Behavior

Mistral.ai should work with all its features.

To Reproduce

1. configure integration_openai with mistral credentials
2. try to use text2speech
3. nextcloud bailes out

Start by tracing how integration_openai handles chat-completion requests and the Mistral API configuration; no source files or tests are named in the issue. Reproduce the reported text-to-speech request with Mistral credentials and use the documented image and speech requirements as the completion criteria.