FAQ: Cannot find module “customtkinter”: Try the exe version here: github.com/0Xiaohei0/VoiceToJapanese/releases/download/v1.2.3/VoiceToJapanese.v1.2.3-exe.zip It requires no setup, just unzip and run the exe file inside. Anti virus may complain about exe files, just click run anyway. If you do not trust the exe file, or want to modify the code, you need to troubleshoot why the setup script failed. This error message means setup.py didn't install the required libraries successfully. Run setup.py and check the console for error message. Most common error is using incorrect python version which should be 3.10. Error loading api key from environment variable, you need an api key from open ai: Check the console for actual error message, if you see "exceeded current quota", it usually means your openai free credits expired. Solution is to upgrade to paid plan, or create new accounts to try and get new free credit. Input: you The transcriber often transcribes silence into "you". Make sure you selected the correct input device in settings and check if the mic meter is moving.
this is incredible, do you know if theres a way to make ignore all the twitch chat bs? people saying single words or emojis, it seems to hyperfixate and waste conversation time
this is fun to use but when i use the mic it detect i am talking but it dosen't detect what words i say and so it can't respond with my voice but overall it was fun to use
Thanks for this comment, for some reason when I tried the banana, it caused the UI to stop loading. Uninstalling audiobananno fixed it and your comment got the audio working.
I have a neat question. Now that we have things like llama.ccp and the ollama interface that let us run local LLMs, is there a way to connect this program to your own local custom model, instead of typing in a chatGPT API key?
I'm aware that this might require a lot of work but is linux support planned? And if not would it be posible for you to tell me which parts would be needed to be "ported" so i can try to do that for myself? Thank you :3
Currently there is no linux support planned. Only whisper have run on your local machine. The other components of the pipeline can be moved to cloud so there shouldn't be any compatibility issues. If you swap out the bundled windows voicevox with the linux version, the project might work, but it's not tested. Also, you would need to install dependencies yourself with console commands.
Actually I just got the program to run on Linux with minimal issues, just need to install some dependencies myself and download the Linux version of voicevox.
I bought it complete on Steam and it came with support for my language "Portuguese" I would like your help to configure it using my language, can you help me? In the tutorial you used Japanese voice, and since mine has Portuguese, how do I use it?
U get some free credits the first time u create an account but remember it stays there for only 3 months so use it all before the trial is over. Mine got wasted unfortunately.
I set up an Elevenlabs account and input the API key into the settings for Elevenlabs for an English voice. When loading the UI, I see on the console it loads both API keys for the AI from Open AI and the API key for the Elevenlabs voices. However, when I send messages to the AI and the AI responds I receive no audio when Elevenlabs is set to 'true'. The console returns this error message: "FileNotFoundError: [winerror 2] the system cannot find the file specified". Any ideas about what is causing the error? Did I miss something on my part that needs additional setup?
I got the text working, why theres no audio from the program? I wonder did I miss something? and Open API also not working... it did not detect my API also I got ffmpeg input error or something
The automated setup script didn’t run successfully, check the console for error message. Most common reason is using incorrect python version which should be 3.10. You can also try the exe version in version 1.2.3.
You can't, I modified the python translator to return the original text in english and it sounds messed up because the app uses voicebox which vocalizes text exclusively in japanese. I'm trying to find solutions to it because I don't want to pay 30 bucks a month just for 2 hours of translation but it's not simple
@@nufh um sorry but I'm not the one who made it I was just reading through comments here. And yes it still works I've been facing some issues (not related to openai) but I managed to fix it. If you face problems I can probably help u. I've tried different projects using openai and all works fine so I don't think the changes did anything. I don't know what are the changes tbh I just came back to mess around with AI after months to maybe revive the AI vtubers again? Who knows. It's been very quiet lately
FAQ:
Cannot find module “customtkinter”:
Try the exe version here: github.com/0Xiaohei0/VoiceToJapanese/releases/download/v1.2.3/VoiceToJapanese.v1.2.3-exe.zip It requires no setup, just unzip and run the exe file inside. Anti virus may complain about exe files, just click run anyway.
If you do not trust the exe file, or want to modify the code, you need to troubleshoot why the setup script failed. This error message means setup.py didn't install the required libraries successfully. Run setup.py and check the console for error message. Most common error is using incorrect python version which should be 3.10.
Error loading api key from environment variable, you need an api key from open ai:
Check the console for actual error message, if you see "exceeded current quota", it usually means your openai free credits expired. Solution is to upgrade to paid plan, or create new accounts to try and get new free credit.
Input: you
The transcriber often transcribes silence into "you". Make sure you selected the correct input device in settings and check if the mic meter is moving.
may I ask the "push to talk" does not work?
@@cc-564 I think its only in 1.2.4 version
so can we use it as a mic?
wow this application development is becoming better and better.
Hello, node_characterai author there. This looks dope man, keep it up!
doing gods work
This is what I need, thank you
this is incredible, do you know if theres a way to make ignore all the twitch chat bs? people saying single words or emojis, it seems to hyperfixate and waste conversation time
If it had filtering then yes, it would be possible. But it doesn't.
code it yourself
did already, its been 6 months@@mimi0010yt
this is fun to use but when i use the mic it detect i am talking but it dosen't detect what words i say and so it can't respond with my voice but overall it was fun to use
you dont need audiobanana for that, at least in windows, just go to sound, recording and in cable output mark the "hear" slot
Thanks for this comment, for some reason when I tried the banana, it caused the UI to stop loading. Uninstalling audiobananno fixed it and your comment got the audio working.
says that i need authorization "Couldn't download, needs authorization"
I have a neat question. Now that we have things like llama.ccp and the ollama interface that let us run local LLMs, is there a way to connect this program to your own local custom model, instead of typing in a chatGPT API key?
Bro i want her in real life. Really.
Thank you!
goodluck im interested also
Thanks
I'm aware that this might require a lot of work but is linux support planned? And if not would it be posible for you to tell me which parts would be needed to be "ported" so i can try to do that for myself? Thank you :3
Currently there is no linux support planned. Only whisper have run on your local machine. The other components of the pipeline can be moved to cloud so there shouldn't be any compatibility issues. If you swap out the bundled windows voicevox with the linux version, the project might work, but it's not tested. Also, you would need to install dependencies yourself with console commands.
Actually I just got the program to run on Linux with minimal issues, just need to install some dependencies myself and download the Linux version of voicevox.
Can a output English or is it just Japanese?
No module named 'customtkinter'
YOU SHOWED AILICE33
Also my thought. Seems he got the model off Steam Workshop?
Huh. neato.
I bought it complete on Steam and it came with support for my language "Portuguese" I would like your help to configure it using my language, can you help me? In the tutorial you used Japanese voice, and since mine has Portuguese, how do I use it?
Does the "Lore" file read even the W++ format? Since it allows to keep informations more organized! Also, is there a way to make her speak English?
You can put elevenlab api key in settings to make her speak English.
Can you read Twitch comments in Spanish and respond in Spanish? @@xiaohei9073
Anyone know of a natural sounding English voice pack I could use for this?
Is there a english version?
I don't know English so that it detects my voice, how can I add other languages that are not just English, Chinese or Japanese?
Do I need to pay for using an open ai api key? As far as I know it does take money from you for some iterations
Let me know if you have to or not please I was also wondering 😅
@@pablobarrios1260 You actually need to pay some cents per interaction
costs money each time you have it generate something. @@pablobarrios1260
No.
U get some free credits the first time u create an account but remember it stays there for only 3 months so use it all before the trial is over. Mine got wasted unfortunately.
is there any way I can work an a german language addon (with both input and output option) and where do I start?
Mate can you please go through it slowly, step by step? im old lol and if u need to, use a TTS to better translate through the language barrier
when i connected the cable to voicemeeter banana the vtube studio mouth tracking stopped working
Can you upload your own model as well or does this only work the model in the video?
This'll work on any model you have. It can also be used on software such as VSeeface.
我超，原（
Hi would there be anyway to connect this to Vseeface over vtube studio since you need to pay for a good vtube model or use default otherwise.
EOF error, RIFF error. Any solution?
i get an error message saying i need to put my api key in a location which i have and even using other api's they all result in the same error
I set up an Elevenlabs account and input the API key into the settings for Elevenlabs for an English voice. When loading the UI, I see on the console it loads both API keys for the AI from Open AI and the API key for the Elevenlabs voices. However, when I send messages to the AI and the AI responds I receive no audio when Elevenlabs is set to 'true'. The console returns this error message: "FileNotFoundError: [winerror 2] the system cannot find the file specified". Any ideas about what is causing the error? Did I miss something on my part that needs additional setup?
how to fix python: can't open file 'C:\\Users\\lilbr\\Downloads\\UI.py': [Errno 2] No such file or directory
Press any key to continue . . .
Can this be used with a local chat model using oobabooga?
how to use subtitles
Do you know how to make the youtube live chat also sound text to speech?
Hello, sir. I tried it and it felt good, but the response speed was too slow. It took more than 6 seconds to ask a question and answer it.
How can you speak to him in Spanish?
portaudioerror(f'error querying device device ') how do i fix this :(
i got it working but the ai key didnt work for some reason and the mouth doesnt move and she doesnt read chat this is so broken
HI! How can I change subtitles for example on Russian,because I can speak Russian, AI answer me on Japanese but subtitles will be in English?
It works for you?
I got the text working, why theres no audio from the program? I wonder
did I miss something? and Open API also not working... it did not detect my API
also I got ffmpeg input error or something
did you solve it? help
my chat isnt working i followed all the steps?
whart source is it in streamlabs?? please help
Can it learn?
i cant hear anything and the vtuber wont say anything
does there english vision?
ENGLISH VERSION??
Why custumkintter
can i use custom voice models?
Only voicevox and eleven lab ones but if u mean custom trained models such as rvc model then no it's not supported yet but you can add it ofc
i need the makise kurisu voice model :c
Bro is about to replicate her irl
I get an error on line 111 of Pyaudio.
helo
how do i change the elevenlab voices
question, how come i cant hear my vtuber?
does this work with RTX2060 6gb?
how can i make her speak english without a paid service?
why do you have file extensions disabled on your system???
the mouth doesnt move?
when i ask her name she replies "Tama", is there a way to change the name? 🙂🙂
You can write "your name is ..." in in lores.txt
can i use my own voice models?
You'd need to add RVC or another similar program to do that
is there no english option
When setting up that chat feature im getting this, any help?
You need an API key stored in an environment variable
If you have put the api key in settings and still getting this error, check console for the actual error.
Pls bro publish it online
Where did you get that vtuber model?
steam workshop
Is there a way to set it up without openai keys? any other github program or actual free website?
if u can add llama llm then it's completely free and people say it's as good as gpt 4 or at least close to it
when I try to start, it says modulenotfounderror: no module named 'customkinter'
The automated setup script didn’t run successfully, check the console for error message. Most common reason is using incorrect python version which should be 3.10. You can also try the exe version in version 1.2.3.
@xiaohei9073 Thanks! I had the wrong version of python running.
@sleezydoodle1053 what python is bad? 3.10 you use?
can this be used in discord?
this doesnt work
how to make it to speak in english?
You can't, I modified the python translator to return the original text in english and it sounds messed up because the app uses voicebox which vocalizes text exclusively in japanese. I'm trying to find solutions to it because I don't want to pay 30 bucks a month just for 2 hours of translation but it's not simple
why do I get an error, can you help? I have installed this program ( import customtkinter
ModuleNotFoundError: No module named 'customtkinter' )
i have the same problem did u find the solution by any chance ?
github.com/0Xiaohei0/VoiceToJapanese/blob/master/README.md#faq
Is there a way to have this on linux?
what to do if Open-AI api is not available in your contry? and cant use vpn ?
need to write code to use another chatbot AI
@@xiaohei9073 and what chatbot ai will that be?
How fast the response?
Depends on ur gpu but I'd say it's usually 3-6 secs
@@SapphireYuna It's been 7 month since you posted it. The program still works? Because there is a change in openai lately.
@@nufh um sorry but I'm not the one who made it I was just reading through comments here. And yes it still works I've been facing some issues (not related to openai) but I managed to fix it. If you face problems I can probably help u. I've tried different projects using openai and all works fine so I don't think the changes did anything. I don't know what are the changes tbh I just came back to mess around with AI after months to maybe revive the AI vtubers again? Who knows. It's been very quiet lately
Is there a way to make it speak english?
Use the eleven labs settings
Does this require DeepL?
why she say in japanese and not in english language?
Use eleven labs
Is not free, api key need to pay 😔
Pls d link
It's in description?