If you already understand all the documentation and can prod an LLM in the correct direction every time it does something stupid then probably.

Why not try it yourself? ;)

OP you are incredibly talented. I believe very few people on earth could do something like that at your age and deliver. Congratulations !

Are there any project which would make TTS with my own voice with some training on my voice ?

While the other commenters provided several voice cloning projects, I would like to point out that I haven't been able to find one that works well for South-American Spanish.

Yes, you can train/fine-tune models on your own voice with Coqui

Elevenlabs, coqui, piper, Microsoft, Google, Apple. Seriously. They all can these days. Don’t forget acapela or nuance.

Yes, elevenlabs can.

I stumbled on this yesterday, it seems to have a queue concept.. https://github.com/ParisNeo/ollama_proxy_server

This looks interesting. However I can't find any documentation on how to program for it ? Where is their documentation about how we use this "unified API" which pools resources between nodes ?

It's somewhere in my git stack :).

Until I get to publishing it, the proto/gRPC definitions for node management are a good enough start: https://github.com/monogon-dev/monogon/blob/main/metropolis/...

And the top level API to actually deploy workloads is plain Kubernetes.

FYI This is a public beta with a wait list. I was not able to access directly.

Same here. When I try to log into Le Chat, I get a message saying “You are on the waitlist. We will let you know when you can start using the app.”

I have been using the Mistral API for the past couple of months, and earlier today I updated my links to use the new endpoints [1]. The small and medium models worked fine through the API, but for several hours the large model failed to respond. When I tried the large model again just now, though, it was working.

It’s evening here in Japan, so I’ll start evaluating the large model’s performance tomorrow.

[1] https://docs.mistral.ai/platform/changelog/

Maybe it was for previous few hours after launch, I just did a normal signup and instant access to large, next and small model

Does work for me, just registered with a Google Account. Perhaps they have troubles with the load and throttle the user inflow because of this. Or could be location-related, I joined from Europe.

I'm building a macro keyboard (4 keys) and was looking for keypads with a display for ages. It seems they are doing it !

This might be relevant to your interests:

https://www.stavros.io/posts/keyyyyyyyys/

i would love something like that for the newest Piaggio MP3 unit... it's really bad

not 'qui me dit', but 'qui me suffit'

Oops (edited my post to fix it).

archive (kind of) https://www.unddit.com/r/personalfinance/comments/10f8042/ba...