AFAIK, Phi-4-multimodal doesn't support TTS, but I understand OP's point.
The recent Qwen's release is an excellent example of model providers collaborating with the local community (which include inference engine developers and model quantizers?). It would be nice if this collaboration extended to wrapper developers as well, so that end-users can enjoy a great UX from day one of any model release.
> it'll probably take a year for the FOSS community to implement and digest it completely
The local community seems to have converged on a few wrappers: Open WebUI (general-purpose), LM Studio (proprietary), and SillyTavern (for role-playing). Now that llama.cpp has an OpenAI-compatible server (llama-server), there's a lot more options to choose from.
I've noticed there really aren't many active FOSS wrappers these days - most of them have either been abandoned or aren't being released with the frequency we saw when OpenAI API first launched. So it would be awesome if you could share your wrapper with us at some point.
Interesting.. In the official API [1], there's no way to prefill the reasoning_content:
> Please note that if the reasoning_content field is included in the sequence of input messages, the API will return a 400 error. Therefore, you should remove the reasoning_content field from the API response before making the API request
So the best I can do is pass the reasoning as part of the context (which means starting over from the beginning).
I've just started experimenting on an AI wrapper that blends companion and assistant into one (think Replika meets Claude), but with an anime-style avatar for the main interface.
As I'm still very early (still in the ideation and prototyping phase), I'd love to hear about experiences that have stuck with you, or any works that got you excited about the possibilities.
As a technical person who recently taught myself frontend from scratch, I found https://web.dev/learn way more structured and thorough. The CSS lesson covers all the essentials and actually made me enjoy working with CSS.
web.dev doesn't get as much love as MDN, but it totally should!
> No system prompt support—the models use the existing chat completion API but you can only send user and assistant messages.
> No streaming support, tool usage, batch calls or image inputs either.
I think it's worth adding a note explaining that many of these limitations are due to the beta status of the API. max_tokens is the only parameter I've seen deprecated in the API docs.
> We will be adding support for some of these parameters in the coming weeks as we move out of beta. Features like multimodality and tool usage will be included in future models of the o1 series.
[0] https://xcancel.com/glitchphoton/status/1927682018772672950