nbth

now you can change the max speed factor ( which affect when tts oversize

Now we have the role-based permission

I'm happy to tell you that the XTTS here has better tts performance

We have a brand new log

Alpha version here the audio is quite bad, which is not good for a podcast but anime is not. Hopefully i can make that better ( maybe not )

Introducing the stage-based pipeline, which helps you resume when a crash occurs. The new TTS lib added is Edge-TTS, not the best at voice cloning, but that good at clear talking

I decide to use F5-TTS for now ( maybe i will add more ). Some finetuned model of F5 have the CC-BY-NC copyright so careful when you use

after many time refactor we can continue to transcript

By some reason the loss is so high, so I decided to use WhisperX to decrease the loss

I try different approaches. By the way, the first pipeline uses Speaker-Diarization-3.1, but I found that when many people talk at the same time, it poses a significant problem. So I switched to vad with pyannote/speech-separation-ami-1.0 and voice embedding to make that more available. In that case, the new solution will take every object to a depth is 1 (But the loss is so high, hopefully that descrease in next devlog)

I hope that lavalink run

We have i8n and lyric searcher ( that not work well) and shuffle and change prefix to l

We have autoplay yeah let go

We have a summary and chat go back ( my credit card is crying, hopefully you don't overuse it, or the https://ai.hackclub.com problem will be solved)

The bot can play music

We have flashcard as the good news
We have this isuess as the bad news https://github.com/hackclub/ai/issues/22 but the pull is some good for this news https://github.com/hackclub/ai/pull/24
i will working for make the chatting come up hope that

I have he quiz collection guy let i try to create something for learn like flashcard

we have the banner yeah

we have markdown let goo yeah

That can look for the emotional transcription maybe that

I am waiting for this pull merged because I am depending on that
https://github.com/hackclub/ai/pull/21

Hello i updated how to use

we have the chat ui let go

I'm adding the anime gif. Yes, sir, wibu forever

I will be working on this project soon when I find the API that can help me create a Discord Bot voice chat ( Whisper -> LLM -> TTS )

I have done with make they run but model tool choose is very bad

Almost done with the backend, now I create the frontend

We starting with login page
i think that fun if we do that