tumblerwarren / virtual_avatar_chatbot

To create a free AI Chatbot/Waifu/ Vtuber that will run on your local computer with minimal GPU requirement.

🌟Yours Truly the AI Virtual Avatar Bot

💬 The Ultimate Companion!

The Goal

To create a free AI Chatbot with visual movement that will run on your local computer with minimal GPU requirement.

Complete Video Installation Guide

Video Link-1 Video Link-2

Steps for installation

• Make sure to install ffmpeg in your computer.
• Install vtube studio.
• Download the zip file.
• Unzip it and rename Example env.txt to .env file using notepad.
• Start Vtube Studio and toggle on "Start Api" from settings.
• Double click to run the start.bat file.
• Allow the plugin in Vtube studio.
• In terminal, when Mic comes, press CTRL and then speak.

Features

• Supports Oogbabooga
• Supoorts betacharacter.ai
• Supports Locall LLM running on Local Machine or Collab

Requirements ✔️✔️

• Above Windows 7
• Python
• C++ Compiler
• Git
• Need help to Install FFmpeg? See this video.
• Find the api key for https://beta.character.ai/ || Need help to find the API key, visit the issue..
• Visual C++ Redistributable for Visual Studio 2015, 2017 and 2019.
• Install VTube Studio.
• Find the API key for elevenlabs.

If you run into any problems, you can go to the following website to report issues.

TROUBLESHOOTING

If you encounter any error or problem, please refer here before pulling an ISSUE.

DOCUMENTATION

• Help for using Voicevox.
• Help for using Oogabooga Text Gen.
• Help for using Local LLM or Collab

🚧 Goals

• Add Voicevox Functionality -- DONE ✅
• Supports Oogabooga Text Gen -- DONE ✅
• Supports Local LLM and Collab LLM inference.
• Running the project without depending on beta.charecter.ai website, by runing llm model locally -- DONE ✅
• Give the waifu an access to the internet -- PENDING ⏳
• All many more.

🤝 Contributions

AI Waifu Assistant is an open-source project, and we welcome any contributions from the community to make it even better! Here are some ways you can contribute:

👉 Bug Reporting: If you encounter any bugs while using the app, please report them in the issues section of the repository. Make sure to provide a clear description of the issue and steps to reproduce it.

🔨 Pull Requests: If you have a fix or improvement that you would like to contribute, you can create a pull request.

📈 Feature Requests: We also welcome feature requests from the community. If you have an idea for a new feature or improvement, you can submit it in the issues section of the repository.

👏 SUPPORT ME!

If you really like the project please support me through PayPal.

🎁 Credits

I used the following projects as my reference. My heartful gratitude to these guys!

😇 THANKS FOR THE SUPPORT!

• Alexander Lewis

📝 REFERENCES:-

desktop-waifu - Your ultimate companion!

CharacterAI - An unofficial API for Character AI for Python using Playwright.

Whisper - Whisper is a general-purpose speech recognition model.

PYVTS - A python library for interacting with the VTube Studio API.

COQUI-AI - TTS is a library for advanced Text-to-Speech generation.

VOICEVOX - The Voicevox Engine

VOICEVOX API - An unofficial API for python

LICENSE

Falls under The MIT License (MIT) Copyright © 2023

virtual_avatar_chatbot's Issues

characterai.errors.NotFoundError

Traceback (most recent call last):
File "F:\Virtual_Avatar_ChatBot-master\main.py", line 120, in
run_program()
File "F:\Virtual_Avatar_ChatBot-master\main.py", line 100, in run_program
main()
File "F:\Virtual_Avatar_ChatBot-master\main.py", line 53, in main
utils.charecter.send_message(transcript)
File "F:\Virtual_Avatar_ChatBot-master\utils\charecter.py", line 17, in send_message
data = client.chat.send_message(CHARECTER_KEY, message_send)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "F:\Virtual_Avatar_ChatBot-master\venv\Lib\site-packages\characterai\characterai.py", line 383, in send_message
info = PostResponse(
^^^^^^^^^^^^^
File "F:\Virtual_Avatar_ChatBot-master\venv\Lib\site-packages\characterai\characterai.py", line 57, in PostResponse
goto(link, wait=wait, token=token)
File "F:\Virtual_Avatar_ChatBot-master\venv\Lib\site-packages\characterai\characterai.py", line 21, in goto
raise errors.NotFoundError(content.split('\n')[-1])
characterai.errors.NotFoundError: The requested resource was not found on this server.

startup shutsdown at the end

Hello, I have downloaded all the required software and put in all the API keys, when I run the startup everything works fine until the end. The mic will record my voice and transcribe it into text but after that the ai does not talk/respond and than the startup command automatically closes are it's done transcribing my voice. @TumblerWarren do you have a discord or anything? I'd love to communicate with you in real time to solve this issue. Thank you.

Failed to build python-crfsuite

Using cached oauthlib-3.2.2-py3-none-any.whl (151 kB)
Building wheels for collected packages: python-crfsuite
Building wheel for python-crfsuite (pyproject.toml) ... error
Failed to build python-crfsuite

Crash

Hello, i have a problem. When i try to run my vtuber it crashes after downloading dependencies. Here is the log(pip is upgraded already).
[notice] A new release of pip available: 22.3.1 -> 23.2.1
[notice] To update, run: python.exe -m pip install --upgrade pip
Running command git clone --filter=blob:none --quiet https://github.com/openai/whisper.git 'C:\Users\nabok\AppData\Local\Temp\pip-req-build-uvialmlv'

[notice] A new release of pip available: 22.3.1 -> 23.2.1
[notice] To update, run: python.exe -m pip install --upgrade pip

[notice] A new release of pip available: 22.3.1 -> 23.2.1
[notice] To update, run: python.exe -m pip install --upgrade pip
Traceback (most recent call last):
File "C:\Users\nabok\Desktop\AI\VTUBER\main.py", line 4, in
import utils.Elevenlabs
File "C:\Users\nabok\Desktop\AI\VTUBER\utils\Elevenlabs.py", line 9, in
ELEVENLABS_API=set_api_key(KEY)
File "C:\Users\nabok\Desktop\AI\VTUBER\venv\lib\site-packages\elevenlabs\simple.py", line 17, in set_api_key
os.environ["ELEVEN_API_KEY"] = api_key
File "C:\Users\nabok\AppData\Local\Programs\Python\Python310\lib\os.py", line 685, in setitem
value = self.encodevalue(value)
File "C:\Users\nabok\AppData\Local\Programs\Python\Python310\lib\os.py", line 743, in check_str
raise TypeError("str expected, not %s" % type(value).name)
TypeError: str expected, not NoneType

Cuando presiono CTRL no graba

Hola, he resuelto el problema de la API de character ai, sin embargo todo se ejecuta bien pero al presionar la tecla para grabar simplemente no pasa nada, espero pueda ayudarme, gracias de antemano.

ai saying out loud action between asterisk

Hello,
Is there a way to make the ai not saying out loud the actions between asterisk ?

Also is it possible to save text chat and pull it back when the session start ?

And last is it possible to integrate TTS Diffusion ?
https://github.com/SicariusSicariiStuff/Diffusion_TTS
Elvenlab is great and all but the limit come too fast and this one has almost elevenlab quality level.

Thanks for the work.

Mic not working when pressing CTRL

Everything works perfectly when i set the program with TEXT but when i use SPEECH the program does not recognize my CTRL so i cant talk to it. Is there any way to change the Key to speak? or any other way to solve this problem?

Elevenlabs Output problem

Hello,

I have a problem with my voice output, your project is working fine, thanks for that!

I can´t use my own created voice from elevenlabs, I don´t really know why but he don´t find my own created voice, the API key is correct and the name also, would it be possible to use it with a elevenlabs voice ID? (Each voice have a ID which allow to search for it)

My second problem is that the voice output is in a british aczent (I have a very well created german voice and the test voice is very good) but if I run the project and she speaks, its in a very british aczent because the script is using the default model instead of the multilangual model, is it possible to change this?
Also that the script is translating all in english when I speak it in german in my microphone, it´s kinda weird to see a english text then hehe

thanks in advance!

Error response

Hi!
I cloned this repo and installed the Python dependencies with

pip install -r requirements.txt

When I booted the app (startup.bat) it asked to connect with VTubeStudio and I allowed API connection.
But the problem comes when I give the mic input. The reponse is as follows:

You (mic) > Hi.
Error Response
AI:
You (mic) >    

The character just sighs and nothing more.

I already defined the ElevenLabs api key in the .env file.
Also, this app is completely liberated in firewall and ativirus.

Also asking: are the keys PYCHAI and CHARECTER_KEY mandatory?

TypeError: str expected, not NoneType

Hello,
I've got a problem. Here is the log:
log.txt

the startup closes at the end suddenly

suddenly closed

I cant get the API key from character ai

Hello, i follow the instructions for get the API key from character AI, but when I enter the command as the instruction says it does not appear, please help me.

The app keeps breaking for no apparent reason

Apparently, after downloading the batch file, it wouldn't install Whisper properly
I then edited the batch file a little to correct the code

For some reason, it still breaks. Even the log doesn't show anything bad

No error code is shown either on the batch file windows or on the log file
Log: log.txt
I cannot submit a screenshot since it happens too quickly for me to take a photo of

PS thanks for responding quickly to our concerns!

Edit: I've stopped npx install playwright or smth like that since it was breaking. Now i'm running into another error

Traceback (most recent call last): File "C:\Users\USER\Downloads\Waifu-master (1)\Waifu-master\main.py", line 5, in <module> import utils.Elevenlabs File "C:\Users\USER\Downloads\Waifu-master (1)\Waifu-master\utils\Elevenlabs.py", line 9, in <module> ELEVENLABS_API=set_api_key(KEY) File "C:\Users\USER\Downloads\Waifu-master (1)\Waifu-master\venv\lib\site-packages\elevenlabs\simple.py", line 9, in set_api_key os.environ["ELEVEN_API_KEY"] = api_key File "C:\Python310\lib\os.py", line 685, in __setitem__ value = self.encodevalue(value) File "C:\Python310\lib\os.py", line 743, in check_str raise TypeError("str expected, not %s" % type(value).__name__) TypeError: str expected, not NoneType

FEATURE: Voicevox

can u pretty pls add voicevox japanese support where it uses voicevox and translates character.ai to japanese so it speaks in japanese in whatever voicevox girl u pick plsplsplsplspslplsplspls

Problem with launch voicevox_startup.bat with llm model

after I passed everything according to the instructions for this and renaming env.txt in .env, I changed, set the requirements, downloaded vtube studio from the api, but still got an error:

You (microphone) > Hello
Error response
AI:
information:     127.0.0.1:58204 - "GET /generate_voice/?text=&speaker_id=2&path=C%3A%5CUsers%5CSevex%5CVirtual_Avatar_ChatBot%5Cutils%5C..%5Cutils%5Cresource%5Cvoice_out%5Cvoicevox. wav HTTP/1.1" 500 Internal Server error
Error: The voice could not be generated. Status code: 500
Feedback (last call):
  File "C:\Users\Sevex\Virtual_Avatar_ChatBot\main.py ", line 177, in <module>
    run_program()
File "C:\Users\Sevex\Virtual_Avatar_ChatBot\main.py ", line 157, in run_program
    main()
File "C:\Users\Sevex\Virtual_Avatar_ChatBot\main.py ", line 89, in main
    utils.vtube_studio.speak()
File "C:\Users\Sevex\Virtual_Avatar_ChatBot\utils\vtube_studio.py ", line 61, in speak
utils.audio.play_wav(memfile, set_audio_level)
  File "C:\Users\Sevex\Virtual_Avatar_ChatBot\utils\audio.py ", line 84, in play_wav
    audio_file = wave.open(path)
                 ^^^^^^^^^^^^^^^
  File "C:\Users\Sevex\AppData\Local\Programs\Python\Python311\Lib\wave.py ", line 631, in plain text
    returns Wave_read(f)
           ^^^^^^^^^^^^
  File "C:\Users\Sevex\AppData\Local\Programs\Python\Python311\Lib\wave.py ", line 279, in __init__
    f = builtins.open(f, 'rb')
        ^^^^^^^^^^^^^^^^^^^^^^
FileNotFoundError: [Error 2] There is no such file or directory: 'C:\\Users\\Sevex\\Virtual_Avatar_ChatBot\\utils\\resource\\Voice_out\\voicevox.wav '
[9100:0109/232554.478:ERROR:gpu_init.cc(486)] End-to-end access is not supported, GL is disabled, the ANGLE is

ALSO here is my .env file

Where should i put beta character key

#Enter your desired chatbot || oogabooga or betacharacter
CHATBOT_SERVICE=betacharacter

#If you have selected chatbot as oogabooga please enter the name of the charceter card you uploaded.
CHARACTER_CARD = Ayaka

#Only if you are using oogabooga, enter your name that you entered while creating Character card. Typically USER,YOU or if have entered your name.
your_name = Warren

#Enter your PyChai API, How to link :- https://pycai.gitbook.io/welcome/api/values
PYCHAI=Enter your charecter.ai API.

#Enter your charecter key, How to link :- https://pycai.gitbook.io/welcome/api/values
CHARECTER_KEY= Charecter Token here

#Enter your Text to Speech Choice | ELEVENLABS or LOCAL_TTS or VOICEVOX(Japanese Only)
TTS_CHOICE = VOICEVOX

#If you have selected Voicevox, enter the voice ID, you can find the voice id from docs VOICEVOX_HELP.
VOICE_ID=2

#Do you have GPU/CUDA, if yes then write True else write False
CUDA_STATUS=True

#Enter your Elevenlabs Api key, How to link :- https://docs.elevenlabs.io/api-reference/quick-start/authentication
ELEVENLAB_KEY= YOUR API

#If you have selected Elevenlabs, enter you model of choice. You can see examples from Elevenlabs website.
VOICE_MODEL=Elli

#Enter your whisper model, see VRAM requirement for further details at whisper Github | tiny, base, small
WHISPER_MODEL=base

#Want to speak in english or your native language | TRANSCRIBE, TRANSLATE
WHISPER_CHOICE=TRANSCRIBE

mic

when i click on ctrl the mic doesn't activate

Python was not found

Python was not found; run without arguments to install from the Microsoft Store, or disable this shortcut from Settings > Manage App Execution Aliases. (i do hv python installed in my system - python 11 )

startup.bat auto close

when the progress it's still loading, it's auto closed

Failed building wheel for TTS

Hi hi, i saw that there were some updates but when i tried them i got an error with the setup

" ERROR: Failed building wheel for TTS
ERROR: Could not build wheels for TTS, which is required to install pyproject.toml-based projects"

I still have an older version of this that works perfectly
log.txt
. But this version gives me this error and crashes afterwards. Is there any solutions?

issues

Traceback (most recent call last):
File "E:\Waifu\main.py", line 109, in
run_program()
File "E:\Waifu\main.py", line 89, in run_program
main()
File "E:\Waifu\main.py", line 46, in main
utils.charecter.send_message(transcript)
File "E:\Waifu\utils\charecter.py", line 17, in send_message
data = client.chat.send_message(CHARECTER_KEY, message_send)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\Waifu\venv\Lib\site-packages\characterai\characterai.py", line 383, in send_message
info = PostResponse(
^^^^^^^^^^^^^
File "E:\Waifu\venv\Lib\site-packages\characterai\characterai.py", line 82, in PostResponse
raise errors.ServerError(response.status_text)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
characterai.errors.ServerError: Unauthorized

Setup.bat files internal links not working.

Fixed the issue update this for people who need it
https://apps.microsoft.com/detail/9PJPW5LDXLZ5?hl=en-us&gl=US

python 3.10 for people who dont know how to install it from zip. Warren maybe updoot the guide with this if needed.

Elevenlabs API issue?

Tried to install but console keeps crashing, got this in my log file

[notice] A new release of pip is available: 23.0.1 -> 23.2.1
[notice] To update, run: python.exe -m pip install --upgrade pip
D:\Waifu-master\venv\Scripts\python.exe: No module named playwright
DEPRECATION: unidic-lite is being installed using the legacy 'setup.py install' method, because it does not have a 'pyproject.toml' and the 'wheel' package is not installed. pip 23.1 will enforce this behaviour change. A possible replacement is to enable the '--use-pep517' option. Discussion can be found at pypa/pip#8559
DEPRECATION: jieba is being installed using the legacy 'setup.py install' method, because it does not have a 'pyproject.toml' and the 'wheel' package is not installed. pip 23.1 will enforce this behaviour change. A possible replacement is to enable the '--use-pep517' option. Discussion can be found at pypa/pip#8559
DEPRECATION: gruut-lang-fr is being installed using the legacy 'setup.py install' method, because it does not have a 'pyproject.toml' and the 'wheel' package is not installed. pip 23.1 will enforce this behaviour change. A possible replacement is to enable the '--use-pep517' option. Discussion can be found at pypa/pip#8559
DEPRECATION: gruut-lang-es is being installed using the legacy 'setup.py install' method, because it does not have a 'pyproject.toml' and the 'wheel' package is not installed. pip 23.1 will enforce this behaviour change. A possible replacement is to enable the '--use-pep517' option. Discussion can be found at pypa/pip#8559
DEPRECATION: gruut-lang-en is being installed using the legacy 'setup.py install' method, because it does not have a 'pyproject.toml' and the 'wheel' package is not installed. pip 23.1 will enforce this behaviour change. A possible replacement is to enable the '--use-pep517' option. Discussion can be found at pypa/pip#8559
DEPRECATION: gruut-lang-de is being installed using the legacy 'setup.py install' method, because it does not have a 'pyproject.toml' and the 'wheel' package is not installed. pip 23.1 will enforce this behaviour change. A possible replacement is to enable the '--use-pep517' option. Discussion can be found at pypa/pip#8559
DEPRECATION: bnunicodenormalizer is being installed using the legacy 'setup.py install' method, because it does not have a 'pyproject.toml' and the 'wheel' package is not installed. pip 23.1 will enforce this behaviour change. A possible replacement is to enable the '--use-pep517' option. Discussion can be found at pypa/pip#8559
DEPRECATION: bnnumerizer is being installed using the legacy 'setup.py install' method, because it does not have a 'pyproject.toml' and the 'wheel' package is not installed. pip 23.1 will enforce this behaviour change. A possible replacement is to enable the '--use-pep517' option. Discussion can be found at pypa/pip#8559
DEPRECATION: gruut-ipa is being installed using the legacy 'setup.py install' method, because it does not have a 'pyproject.toml' and the 'wheel' package is not installed. pip 23.1 will enforce this behaviour change. A possible replacement is to enable the '--use-pep517' option. Discussion can be found at pypa/pip#8559
DEPRECATION: audioread is being installed using the legacy 'setup.py install' method, because it does not have a 'pyproject.toml' and the 'wheel' package is not installed. pip 23.1 will enforce this behaviour change. A possible replacement is to enable the '--use-pep517' option. Discussion can be found at pypa/pip#8559
DEPRECATION: pyvts is being installed using the legacy 'setup.py install' method, because it does not have a 'pyproject.toml' and the 'wheel' package is not installed. pip 23.1 will enforce this behaviour change. A possible replacement is to enable the '--use-pep517' option. Discussion can be found at pypa/pip#8559

[notice] A new release of pip is available: 23.0.1 -> 23.2.1
[notice] To update, run: python.exe -m pip install --upgrade pip
Traceback (most recent call last):
File "D:\Waifu-master\main.py", line 4, in
import utils.Elevenlabs
File "D:\Waifu-master\utils\Elevenlabs.py", line 9, in
ELEVENLABS_API=set_api_key(KEY)
File "D:\Waifu-master\venv\lib\site-packages\elevenlabs\simple.py", line 10, in set_api_key
os.environ["ELEVEN_API_KEY"] = api_key
File "C:\Python310\lib\os.py", line 685, in setitem
value = self.encodevalue(value)
File "C:\Python310\lib\os.py", line 743, in check_str
raise TypeError("str expected, not %s" % type(value).name)
TypeError: str expected, not NoneType

[notice] A new release of pip is available: 23.0.1 -> 23.2.1
[notice] To update, run: python.exe -m pip install --upgrade pip
Running command git clone --filter=blob:none --quiet https://github.com/openai/whisper.git 'C:\Users\kaj7\AppData\Local\Temp\pip-req-build-c7wty_4y'

[notice] A new release of pip is available: 23.0.1 -> 23.2.1
[notice] To update, run: python.exe -m pip install --upgrade pip

[notice] A new release of pip is available: 23.0.1 -> 23.2.1
[notice] To update, run: python.exe -m pip install --upgrade pip
Traceback (most recent call last):
File "D:\Waifu-master\main.py", line 4, in
import utils.Elevenlabs
File "D:\Waifu-master\utils\Elevenlabs.py", line 9, in
ELEVENLABS_API=set_api_key(KEY)
File "D:\Waifu-master\venv\lib\site-packages\elevenlabs\simple.py", line 10, in set_api_key
os.environ["ELEVEN_API_KEY"] = api_key
File "C:\Python310\lib\os.py", line 685, in setitem
value = self.encodevalue(value)
File "C:\Python310\lib\os.py", line 743, in check_str
raise TypeError("str expected, not %s" % type(value).name)
TypeError: str expected, not NoneType

[notice] A new release of pip is available: 23.0.1 -> 23.2.1
[notice] To update, run: python.exe -m pip install --upgrade pip
Running command git clone --filter=blob:none --quiet https://github.com/openai/whisper.git 'C:\Users\kaj7\AppData\Local\Temp\pip-req-build-r2zrpbct'

[notice] A new release of pip is available: 23.0.1 -> 23.2.1
[notice] To update, run: python.exe -m pip install --upgrade pip

[notice] A new release of pip is available: 23.0.1 -> 23.2.1
[notice] To update, run: python.exe -m pip install --upgrade pip
Traceback (most recent call last):
File "D:\Waifu-master\main.py", line 4, in
import utils.Elevenlabs
File "D:\Waifu-master\utils\Elevenlabs.py", line 9, in
ELEVENLABS_API=set_api_key(KEY)
File "D:\Waifu-master\venv\lib\site-packages\elevenlabs\simple.py", line 10, in set_api_key
os.environ["ELEVEN_API_KEY"] = api_key
File "C:\Python310\lib\os.py", line 685, in setitem
value = self.encodevalue(value)
File "C:\Python310\lib\os.py", line 743, in check_str
raise TypeError("str expected, not %s" % type(value).name)
TypeError: str expected, not NoneType

[notice] A new release of pip is available: 23.0.1 -> 23.2.1
[notice] To update, run: python.exe -m pip install --upgrade pip
Running command git clone --filter=blob:none --quiet https://github.com/openai/whisper.git 'C:\Users\kaj7\AppData\Local\Temp\pip-req-build-iapa0y9c'

[notice] A new release of pip is available: 23.0.1 -> 23.2.1
[notice] To update, run: python.exe -m pip install --upgrade pip

[notice] A new release of pip is available: 23.0.1 -> 23.2.1
[notice] To update, run: python.exe -m pip install --upgrade pip
Traceback (most recent call last):
File "D:\Waifu-master\main.py", line 4, in
import utils.Elevenlabs
File "D:\Waifu-master\utils\Elevenlabs.py", line 9, in
ELEVENLABS_API=set_api_key(KEY)
File "D:\Waifu-master\venv\lib\site-packages\elevenlabs\simple.py", line 10, in set_api_key
os.environ["ELEVEN_API_KEY"] = api_key
File "C:\Python310\lib\os.py", line 685, in setitem
value = self.encodevalue(value)
File "C:\Python310\lib\os.py", line 743, in check_str
raise TypeError("str expected, not %s" % type(value).name)
TypeError: str expected, not NoneType

any help would be greatly appreciated!

There is a way to read the twitch chat and my voice at the same time?

i'm really newbie for this, i made the bot to read the chat from twitch, but for some reason can't hear me, but if i disable the twitch option it hear me

start up still closes at the end pt.3 bug

StartApp_log.txt

From Log I can see that it has some issues with ELEVENLABS but VOICEVOX is selected.

#Enter your input choice || Speech or Text
INPUT_CHOICE=Text

#Enter your desired chatbot || oogabooga or betacharacter or local_llm or collab_llm
CHATBOT_SERVICE=local_llm

#Enter the Ngrok URL which you have got from Google Collab.
ngrok_url=https://90d8-34-32-215-157.ngrok-free.app

#If you have selected chatbot as oogabooga please enter the name of the charceter card you uploaded.
CHARACTER_CARD = Ayaka

#Only if you are using oogabooga, enter your name that you entered while creating Character card. Typically USER,YOU or if have entered your name.
your_name = Warren

#Enter your PyChai API, How to link :- https://pycai.gitbook.io/welcome/api/values
PYCHAI=

#Enter your charecter key, How to link :- https://pycai.gitbook.io/welcome/api/values
CHARECTER_KEY=

#Enter your Text to Speech Choice | ELEVENLABS or VOICEVOX(Japanese Only) |LOCAL_TTS is out of support now,I will add it after fixing the problem
TTS_CHOICE = VOICEVOX

#If you have selected Voicevox, enter the voice ID, you can find the voice id from docs VOICEVOX_HELP.
VOICE_ID=2

#Do you have GPU/CUDA, if yes then write True else write False
CUDA_STATUS=True

#Enter your Elevenlabs Api key, How to link :- https://docs.elevenlabs.io/api-reference/quick-start/authentication
ELEVENLAB_KEY=

#If you have selected Elevenlabs, enter you model of choice. You can see examples from Elevenlabs website.
VOICE_MODEL=

#Enter your whisper model, see VRAM requirement for further details at whisper Github | tiny, base, small
WHISPER_MODEL=base

#Want to speak in english or your native language | TRANSCRIBE, TRANSLATE
WHISPER_CHOICE=TRANSCRIBE

Python was not found; run without arguments to install from the Microsoft Store, or disable this shortcut from Settings > Manage App Execution Aliases.

I have python 3.10 (64bit), why am i getting this error?

StartApp_log.txt

Failing to get this working

Getting this error with the setup.bat

Getting this error with LLM_Inference

startup.bat crashing

AI reply text and app close, in log.txt found module named 'colorama'. But colorama existing in site-packages

Hi Warren,

I config .env CHATBOT_SERVICE=betacharacter
After run Start_App.bat. I can speak and AI can reply. But after AI reply, app was closed.
I check log.txt, I found ModuleNotFoundError: No module named 'colorama' and others error.
colorama ready installed, I found on ...\Virtual_Avatar_ChatBot-master\venv\Lib\site-packages
Please suggestion

log.txt

start up still closes at the end pt.2

@TumblerWarren hello I uninstalled python 3.12 and downloaded python 3.10 and the same issue still happens where after my mic records and transcribes my voice the start program will just suddenly close.

log
log.txt

macos

how can i use this on a macbook pls ?

Could not find module 'E:...\Virtual_Avatar_ChatBot-master\venv\Lib\site-packages\torchaudio\lib\libtorchaudio.pyd

Hello!

When I run startup.bat, the window closes and the following error occurs:

• log.txt

Please tell me what could be the error?

Help

When I try to run Setup.bat, after a while an error appears saying Failed to build TTS. and I don't know what to do

[Feature request] Ability to use custom Elevenlabs voices

How do we use custom eleven voices? I've tried to modify elevenlabs.py file....

No module named 'greenlet._greenlet'

I redownloaded the repo and this happened
Here's the log file: log.txt

Not working lol

I started setup, let it complete, then i started the Start_App.bat. No Interface is Opening, only CMD showing None

Startup not working

Been trying to get this to work but hit a hurdle on the startup bat file stopping without any error, any ideas? here's the log
log.txt

elevenlabs character limit

Hello @TumblerWarren , thank you for the solutions to my previous issues, the program works perfectly fine now, you were right I had the character API and the token switched which was the issue. I was wondering if there was any way for you to find a way for a free alternative to elevenlabs because currently elevenlabs has a free monthly character limit of 10,000 a month and I am already at 4000. So I was wondering if you could add a free alternative to where the program could be run with no limitations or restrictions. Perhaps some sort of free unlimited TTS similar to elevenlabs?
Thank you.

Again ...failing to get this working

UPDATE
Ok finally got passed the issue after reinstalling my Visual Studio and C++ build tools. Not sure why that happened