koischizo / ai-vtuber Goto Github PK

Hi, I'm a beginner. May I ask what should I fill in this field?

"EL_data": [
{
"voice": "MF3mGyEYCl7XYWbV9V6O"
}
]

I have already obtained the "EL_key", but I don't know how to use it later. Please help.

I have installed pip install pytchat, but still like that

PS C:\Users\60107\Downloads\AI-Vtuber-main> & "C:/Program Files/Python311/python.exe" c:/Users/60107/Downloads/AI-Vtuber-main/AI-Vtuber-main/run.py
C:\Users\60107\AppData\Roaming\Python\Python311\site-packages\pydub\utils.py:170: RuntimeWarning: Couldn't find ffmpeg or avconv - defaulting to
ffmpeg, but may not work
warn("Couldn't find ffmpeg or avconv - defaulting to ffmpeg, but may not work", RuntimeWarning)
Unable to open JSON file.

I have no idea how to code and there so I can't even get past the github link. can someone please just tell me how to do it lol

Tried executing run command through powershell and gave me an error saying Unable to open JSON how do I fix this?

File "C:\Users\AI TESTER\Desktop\AI-Vtuber-main.venv\lib\site-packages\win32\lib\pywintypes.py", line 116, in import_pywin32_system_module
mod = importlib.util.module_from_spec(spec)
ImportError: DLL load failed: The specified module could not be found.
(.venv) PS C:\Users\AI TESTER\Desktop\AI-Vtuber-main>

I have an issue on run.py's line 105→chat = pytchat.create(video_id=video_id)
error:
Exception has occurred: TypeError
argument of type 'NoneType' is not iterable
File "C:\ai gf\desktop-waifu-master\AI-Vtuber-main\run.py", line 105, in read_chat
chat = pytchat.create(video_id=video_id)
File "C:\ai gf\desktop-waifu-master\AI-Vtuber-main\run.py", line 149, in
read_chat()
TypeError: argument of type 'NoneType' is not iterable

"ai gf\desktop-waifu-master"is my folder name don't judge.

Hey im getting this error:

C:\Users\user\AppData\Local\Programs\Python\Python310\lib\site-packages\pydub\utils.py:170: RuntimeWarning: Couldn't find ffmpeg or avconv - defaulting to ffmpeg, but may not work
warn("Couldn't find ffmpeg or avconv - defaulting to ffmpeg, but may not work", RuntimeWarning)

I have ffmpeg installed and don't know what to do.
Thank you!

I know how to get the api token for twitch chat but can anyone help me with replacing the code in the project?

I get an error while trying to install the requirements, specifically with simpleaudio.

It says,
python setup.py bdist_wheel did not run successfully.
ERROR: Failed building wheel for simpleaudio

Sorry, I am new to this, if anyone knows what the problem is or knows what to do I would appreciate it very much, thank you.

Hello, the voice always has an english accent even if he speaks another language, so is it possible to add the Eleven Multilingual version?

Call json ok on MAC SO, but jump out of Process: Unable to open JSON file in win environment.

Please help me to solve the problem

openai.error.AuthenticationError: You didn't provide an API key. You need to provide your API key in an Authorization header using Bearer auth (i.e. Authorization: Bearer YOUR_KEY), or as the password field (with blank username) if you're accessing the API from your browser and are prompted for a username and password. You can obtain an API key from https://platform.openai.com/account/api-keys.

but i do change the API key

Hey! Thanks again for sharing this project, wanted to ask a question about this error Im getting.

File "C:\Users\user\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\LocalCache\local-packages\Python311\site-packages\openai\api_requestor.py", line 682, in _interpret_response_line
raise self.handle_error_response(
openai.error.RateLimitError: You exceeded your current quota, please check your plan and billing details.

Do I need to make a paid account to use this?

i have added STREAMID correctly, but still failed
raise InvalidVideoIdException(f"Invalid video id: {url_or_id}")
pytchat.exceptions.InvalidVideoIdException: Invalid video id: STREAMID

how to let my avatar's mouth move as the ai is talking?

Please add comments so I can understand it better
Add some comments on where things happen and what

Hello, I don't want to use eleven labs, so I want to modify the pyttx3 voice to Spanish but I don't know how to make this change, I would appreciate your help

ERROR: Could not build wheels for simpleaudio, which is required to install pyproject.toml-based projects

I can't find any way to fix this error help me for this error @Koischizo

As a total coding noob (have absolutely no coding experience for Python), I got the EL TTS working and changed the voice ID for my EL and it sounds perfect. The responses are very "human-like" as well but the only thing is can I connect this to my Twitch channel instead of YouTube? Many thanks in advance!

How would I go about adding twitch chat into the code? With the option to let the AI read both chats at the same time or for me to just decide which one it should read, would that be a possible thing to add to the code?

Thanks for sharing this project, but I can't seem to get pytchat to work. I have installed pytchat with the command pip install pytchat but whenever I try to run the code with run.py, i get this error: ModuleNotFoundError: No module named 'pytchat'
any help is appreciated, thanks.

raise CouldntDecodeError(

pydub.exceptions.CouldntDecodeError: Decoding failed. ffmpeg returned error code: 1

shows this issue it was working fine and recently started showing this issue

can someone help me pls i got this error and i tryed everything

C:\Users\pc name\AI-Vtuber>C:\Users\pc name\AI-Vtuber\run.py
Traceback (most recent call last):
File "C:\Users\pc name\AI-Vtuber\run.py", line 145, in
initVar()
File "C:\Users\pc name\AI-Vtuber\run.py", line 66, in initVar
initTTS()
File "C:\Users\pc name\AI-Vtuber\run.py", line 21, in initTTS
engine.setProperty('voice', voice[1].id)
~~~~~^^^
IndexError: list index out of range

Im having one trouble man my program is working totally fine just somewhere have problem in audio or maybe im not good at doing settings so its actually generating text but not talking and not moving lips also and pls tell which software you are using for streaming ?

Firstly, thanks for share the..vtuber code..btw
Please, could explain more.. detail? I understand the concept but it s really hard to follow
I did until set the API key but.. I have no idea how to set the voice in here https://beta.elevenlabs.io/
cuz they do not allow me to set the voice.
and if I want to try should just type "python run.py" wih CMD?

HOW TO CHANGE THE VOICE, IN ELEVENLABS THERE IS ONLY ID

please make a tutorial, step by step on how to do this
total beginner, never understood coding, so please.
also thanks for open sourcing the codes :)

how to solve this error?

File "run.py", line 84
url = f'https://api.elevenlabs.io/v1/text-to-speech/{EL.voice}'

Goose AI offers API services for GPT Neo/GPT J and its much cheaper than OPEN AI. I don't have much experience on LLMs and I think the AI will be more based and sassy as I've seen from YouTube videos. Not familiar on how to setup filters for words and topics the AI will avoid.

i am a total beginner, the program was working fine but lately after the first messages, or sometimes even at the first one, i get this message and the program crashes

libavutil 58. 2.100 / 58. 2.100
libavcodec 60. 3.100 / 60. 3.100
libavformat 60. 3.100 / 60. 3.100
libavdevice 60. 1.100 / 60. 1.100
libavfilter 9. 3.100 / 9. 3.100
libswscale 7. 1.100 / 7. 1.100
libswresample 4. 10.100 / 4. 10.100
libpostproc 57. 1.100 / 57. 1.100
[cache @ 000001c2b6453340] Inner protocol failed to seekback end : -40
Last message repeated 1 times
[mp3 @ 000001c2b6455ac0] Failed to read frame size: Could not seek to 1239.
[cache @ 000001c2b6453340] Statistics, cache hits:2 cache misses:1
cache:pipe:0: Invalid argument

i have tried updating ffmepg but it doesn't work and if i search online there seem to be different problems, so i don't really know what to do

First thing, I gotta say this source is awesome, mad respect to you Shizo, but theres only an issue that I cant really find anything about it, basically the system works just fine with the default tts (without Eleven Labs pretty much), so I wanted to try it with the EL thing, it worked all fine, it gave the answer, but the answer did not play audio, and after some seconds, it throws up an error that basically says this: "PermissionError: [Errno 13] Permission denied: 'C:\Users\user\AppData\Local\Temp\tmpdrrn9z31.wav'", already tried some solutions I found to related issues about this, but none worked, and again, its an issue with playing Eleven Labs audio, the one with the default TTS works just fine, thank you for this still! Gotta wait for an answer :)

So i try to run pip install -r requirements.txt and everthing is fine except simpleaudio, it said
× Encountered error while trying to install package.
╰─> simpleaudio
simpleaudio is matters for this program or not. If yes, how do i fix it.
Thanks you and sorry for my poor english.