Hey! Before I buy it I just want to know if I can only do bits/donations that my png reacts too. SO every time someone donates and the TTS happens, can I connect them?
heya! yep! you can decided what stuff your pet reads/reacts to. I recommend people with high viewers average to limit it only to bits and donos to prevent spam. For donos depending on the donos you use, you may need to connect vtspog to mixitup or streamerbot so they send the dono event data to vtspog, but its doable. If you need help with that feel free to come over to the discord server and I can guide you through that with any of those programs as an in between~ (link to discord server on vtspog itself at the bottom of the side menu)
Hello! I'm not sure if this is something you have control over but maybe at least you could forward this to the right place. The StreamElements voices for German, Albert, Oskar, and Sebastian are suddenly all the same when they definitely weren't before. I used Sebastian for my TTS Pet and now that the voice is different, my community is very sad :(
heya! I tried reported this to stream elements but got now response for them a few weeks back. Probably about time to do a second report soon... Sadly yeah, outside my control I'm afraid D: the list of voices affected is a bit longer too
hello!! i love vts p.o.g. and have been using it for a year or so, i recently moved my alerts over to twitch alerts and was wondering if it will work with the twitch alerts soon for the TTS? if not totally fine, i was just wondering !
heya! tbh I have seen nothing about twitch alerts as a system, given I saw a lot of overlap between that and the default twitch connection for third party apps like vtspog, and some other "event catchers" programs like mixitup or streamerbot (which vtspog already connects to). Would have to do some testing and see what exactly those provide timing or event wise in comparison with those, so I wouldn't discard it but I feel that for most cases those other options should cover em already (I might be mistaken though! )
its possible though the setup its a bit trick. Mixitup or streamerbot as an inbetween would be needed. If you can come over to the discord server (link in vtspog at the bottom of the side menu), make a thread over on support and explain the setup in detail you are aiming to achive and I would advice you/guide you on how to set it up as best as I can
heya! probably obs is not capturing vtspog audio correctly. Here in the docs there's a couple of ways listed on how to capture vtspog audio with obs(most of them also apply to streamlabs desktop too)
I have an issue where the 'pet' won't respond to a question unless I restart the program. It seems to happen after a while without anyone using the redeem. How do I avoid this?
heya! hard to say with just that. I would need a bit more info to try to figure out what mayt be failing. Can you come over to our discord server and make a support thread over there explaining the issue in as much detail as possible? Hopefully we can figure out whats happening together
Hello, I'm not sure why I'm having this issue or if anyone else is encountering this. When I go to test reactions to a alert reaction for the mascot it only works once and then never again for any of the alerts. I don't know what I did to break it but I've been watching tutorials for hours and nothing is working.
heya! I sorry, I can quite understand the specific issue you are having. It will be best if you come over to our discord server and make a thread on the support channel there (ideally with a video showing the issue) and we can give it a look together. Watching the error/issue in motion helps a lot for me to understand what may be happening 🙏
Heya! Got this quite a while ago. Didn't have a chance to use it. Was planning to this year... But I ran into a problem.
I was planning to use a voice from ElevenLabs, but they've turned it into a "Legacy" voicebank, meaning it doesn't show up in the menu anymore. It seems this can be fixed easily, just by setting a flag when connecting to their API. Think you can implement this in a future update?
heya! can you come over to our discord server and get a bit into detail of the issue on a support thread there? Not fully understanding the situation atm but if there's a quick solution to it sure. I would need more details in order to replicate the issue myself for a start.
i am gettering a message "VTS P.O.G. found an error during warm up! Please restart the program, that tends to do the trick." trying multiple times trying as admin and even fully uninstalling and reinstalling it doesnt work it still gives the same issue
heya! hard to say with just that. If you can come over to our discord server (link in the itchio page) you can make a thread on support there and we can try to figure out together what may be wrong. When you make the thread, please also share there a recording showing your full screen since before opening vtspog, then opening and triggering that error so I can have a better idea of the whole situation and we can see from there ♥
Hello there! I'm a non-mic streamer who wanted to add audio to my chat, and VTS POG is working excellently for my needs so far. I use Chroneco's OnStreamChat program to link phrases (and text emotes!) up to different expressions for a PNGtuber model.
I'd like to keep the text emotes silent while still using them, although haven't found any way to silence them properly. In Moderation Settings, "Don't read emoji" only works for emojis proper. "Banned words" also doesn't filter text emotes, but - presumably being meant for actual moderation - will otherwise filter an entire message outright.
(I tested this with the following text emotes: ^.^; ~ ^.^ ~ :) ~ ;-; ~ D: ~ *u* )
Is there a way for VTS POG to filter text emotes or other very select text at the moment, or plans to add one in the future? I'm on VTS POG version 2.0.18, if that helps.
There's no rush! Either way, thank you so much for the program!
I'm interested in this but I want to continue using speakerbot as my method of using TTS which is sent to a virtual audio cable and I'm not seeing that this allows for getting that for moving the model. Is there any plans for allowing such things? For what it's worth, I am using Azure Cognitive Services for the TTS since I'm able to adjust the voice for what I want it and speakerbot just gives me a bit more flexibility for that as well.
heya! not atm but its something that was a feature back in beta on 2022 that I want to re-add again. We have support for azure tts, but its a bit more barebones compared to speaker bot. TLDR; not working with speakerbot atm, but a feature will allow it soon
Hello! I love this program so much, thank you so much for your hard work!
I was wondering do you plan on adding to the customization of captions? Maybe curving the edges, making the text box into different shapes, or adding an image background to it?
One of the many things on my eternal to do list but for sure. MORE caption options are must D: there's simple not enough good ones atm indeed. Someday for sure!
Is there a way to block or prevent engagement with specific users? I have someone on my stream who keeps grooming my pet to say really dumb things that goes against her personality. I have to reset her memory frequently so that she'll stop being cringe for this user's enjoyment. I don't want to ban the person but it's getting very annoying to deal with it every stream
heya! thats super werid! You can find a link to our discord server on the main page https://vtspog.com , feel free to make a thread on support there and we can give ya a hand over there to try to make it work. I'm positive we can figure it out if we check it out together ♥
heya! you need to download the new version and just unzip the file and either replace the folder or delete the old one and just use the new one. VTS P.O.G. saves configuration on windows appdata so configs carry over between versions, they are not saved on the vtspog folder..
little experience myself in mac development so I wouldnt even know where to start with that, sadly a bit outside of my knowledge as a developer. I'm planning on getting a mac around February (hopefully) to adapt vtspog for mac cause I don't even have one myself and are a bit hard/expensive to get where I live (Argentina)
not a linux user myself, so low experience in adapting it to it BUT one of our users made a guide on how to run it on linux. I wasnt able to try it myself, but seems to be working after many hoops! Let me link the video they made going through their setup here
not atm, but ollama support is in the works, so far the most stable option for local llm I have found. If you know coding, you can also send generated responses to vtspog through our local api, but the setup may be a bit complex unless you are confident in your python (given most local llm model solutions run in python)
for the openai stuff why just make the b ase url customizable so we can use lmstudios server
# Chat with an intelligent assistant in your terminalfrom openai import OpenAI # Point to the local server client = OpenAI(base_url="http://localhost:1234/v1", api_key="lm-studio") history = [ {"role": "system", "content": "You are an intelligent assistant. You always provide well-reasoned answers that are both correct and helpful."}, {"role": "user", "content": "Hello, introduce yourself to someone opening this program for the first time. Be concise."}, ] whileTrue: completion = client.chat.completions.create( model="model-identifier", messages=history, temperature=0.7, stream=True, ) new_message = {"role": "assistant", "content": ""} for chunk in completion: if chunk.choices[0].delta.content: print(chunk.choices[0].delta.content, end="", flush=True) new_message["content"] += chunk.choices[0].delta.content history.append(new_message) # Uncomment to see chat history# import json# gray_color = "\033[90m"# reset_color = "\033[0m"# print(f"{gray_color}\n{'-'*20} History dump {'-'*20}\n")# print(json.dumps(history, indent=2))# print(f"\n{'-'*55}\n{reset_color}")print() history.append({"role": "user", "content": input("> ")})
if they use the openai api we the base url can be changed and can run a server with lmstudio that be dope if they can update and use xtts-api-server also
didnt know about lms studio or coqui so i would need to give em a check, but I'm always open to suggestions. Will try giving em a look once I have the time~
As a vtuber I'm interested in this program, since it looks cool and also interesting way to interact with a chat.And also, I saw the Vnyan integration on twitter.
But do you plan any language update? For example Ukrainian? Unfortunately, not so many TTS working with this language and it's a bit upset.
heya! sadly the vast majority of voices available around are in english, the market is way too focused there. We have in streamelements and azure tts voices in ukranian but only 3 with them added up (and quality tbh cant compare to the english ones). So we have some ukranian voices, just not many D:
← Return to vtube studio plugin
Comments
Log in with itch.io to leave a comment.
Hey! Before I buy it I just want to know if I can only do bits/donations that my png reacts too. SO every time someone donates and the TTS happens, can I connect them?
heya! yep! you can decided what stuff your pet reads/reacts to. I recommend people with high viewers average to limit it only to bits and donos to prevent spam. For donos depending on the donos you use, you may need to connect vtspog to mixitup or streamerbot so they send the dono event data to vtspog, but its doable. If you need help with that feel free to come over to the discord server and I can guide you through that with any of those programs as an in between~ (link to discord server on vtspog itself at the bottom of the side menu)
Hello! I'm not sure if this is something you have control over but maybe at least you could forward this to the right place. The StreamElements voices for German, Albert, Oskar, and Sebastian are suddenly all the same when they definitely weren't before. I used Sebastian for my TTS Pet and now that the voice is different, my community is very sad :(
heya! I tried reported this to stream elements but got now response for them a few weeks back. Probably about time to do a second report soon... Sadly yeah, outside my control I'm afraid D: the list of voices affected is a bit longer too
Thank you so much! I hope they get to it...
hello!! i love vts p.o.g. and have been using it for a year or so, i recently moved my alerts over to twitch alerts and was wondering if it will work with the twitch alerts soon for the TTS? if not totally fine, i was just wondering !
heya! tbh I have seen nothing about twitch alerts as a system, given I saw a lot of overlap between that and the default twitch connection for third party apps like vtspog, and some other "event catchers" programs like mixitup or streamerbot (which vtspog already connects to). Would have to do some testing and see what exactly those provide timing or event wise in comparison with those, so I wouldn't discard it but I feel that for most cases those other options should cover em already (I might be mistaken though! )
Hello! Is it possible to use 2 languages of TTS at the same time (bilingual chat)? (ru/en)
If so, how can I setup this or what can I try to do?
its possible though the setup its a bit trick. Mixitup or streamerbot as an inbetween would be needed. If you can come over to the discord server (link in vtspog at the bottom of the side menu), make a thread over on support and explain the setup in detail you are aiming to achive and I would advice you/guide you on how to set it up as best as I can
Thank you! I will do
Hi, I've set this up and I can hear it just fine, but nobody in my Twitch chat can, was wondering if there's any info on how to fix this please?
heya! probably obs is not capturing vtspog audio correctly. Here in the docs there's a couple of ways listed on how to capture vtspog audio with obs(most of them also apply to streamlabs desktop too)
https://vtspog.com/docs/article/audio-configuration/
I have an issue where the 'pet' won't respond to a question unless I restart the program. It seems to happen after a while without anyone using the redeem.
How do I avoid this?
heya! hard to say with just that. I would need a bit more info to try to figure out what mayt be failing. Can you come over to our discord server and make a support thread over there explaining the issue in as much detail as possible? Hopefully we can figure out whats happening together
Hello, I'm not sure why I'm having this issue or if anyone else is encountering this. When I go to test reactions to a alert reaction for the mascot it only works once and then never again for any of the alerts. I don't know what I did to break it but I've been watching tutorials for hours and nothing is working.
heya! I sorry, I can quite understand the specific issue you are having. It will be best if you come over to our discord server and make a thread on the support channel there (ideally with a video showing the issue) and we can give it a look together. Watching the error/issue in motion helps a lot for me to understand what may be happening 🙏
Thank you. Do you happen to have the link to the discord? I might be blind and the link might be in plain sight but I can't seem to find it.
sorry, somehow missed this message. You can find a link to our server on the itchio mainpage or on vtspog itself (down the bottom of the side menu)
Heya! Got this quite a while ago. Didn't have a chance to use it. Was planning to this year... But I ran into a problem.
I was planning to use a voice from ElevenLabs, but they've turned it into a "Legacy" voicebank, meaning it doesn't show up in the menu anymore. It seems this can be fixed easily, just by setting a flag when connecting to their API. Think you can implement this in a future update?
heya! can you come over to our discord server and get a bit into detail of the issue on a support thread there? Not fully understanding the situation atm but if there's a quick solution to it sure. I would need more details in order to replicate the issue myself for a start.
Gotcha. I'll try to open one ASAP!
Any updates regarding mac development? I have a stream pet that I'd love to use TTS for, but alas, I am stuck with a mac for now.
If no updates, is there an equivalent available that you know of?
no news yet and no that I'm aware of I'm afraid D:
i am gettering a message "VTS P.O.G. found an error during warm up! Please restart the program, that tends to do the trick." trying multiple times trying as admin and even fully uninstalling and reinstalling it doesnt work it still gives the same issue
heya! hard to say with just that. If you can come over to our discord server (link in the itchio page) you can make a thread on support there and we can try to figure out together what may be wrong. When you make the thread, please also share there a recording showing your full screen since before opening vtspog, then opening and triggering that error so I can have a better idea of the whole situation and we can see from there ♥
Hello there! I'm a non-mic streamer who wanted to add audio to my chat, and VTS POG is working excellently for my needs so far. I use Chroneco's OnStreamChat program to link phrases (and text emotes!) up to different expressions for a PNGtuber model.
I'd like to keep the text emotes silent while still using them, although haven't found any way to silence them properly. In Moderation Settings, "Don't read emoji" only works for emojis proper. "Banned words" also doesn't filter text emotes, but - presumably being meant for actual moderation - will otherwise filter an entire message outright.
(I tested this with the following text emotes: ^.^; ~ ^.^ ~ :) ~ ;-; ~ D: ~ *u* )
Is there a way for VTS POG to filter text emotes or other very select text at the moment, or plans to add one in the future? I'm on VTS POG version 2.0.18, if that helps.
There's no rush! Either way, thank you so much for the program!
heya! happy to hear that its working for non-mic streamers ♥♥
And yes! Filtering twitch emotes is in my todo list, its just something tricky to properly do tbh. But its coming!
Excellent, thank you! I have a habit of using some custom text emotes, so I'm looking forward to it. ^.^
I'm interested in this but I want to continue using speakerbot as my method of using TTS which is sent to a virtual audio cable and I'm not seeing that this allows for getting that for moving the model. Is there any plans for allowing such things? For what it's worth, I am using Azure Cognitive Services for the TTS since I'm able to adjust the voice for what I want it and speakerbot just gives me a bit more flexibility for that as well.
heya! not atm but its something that was a feature back in beta on 2022 that I want to re-add again. We have support for azure tts, but its a bit more barebones compared to speaker bot. TLDR; not working with speakerbot atm, but a feature will allow it soon
Hello! I love this program so much, thank you so much for your hard work!
I was wondering do you plan on adding to the customization of captions? Maybe curving the edges, making the text box into different shapes, or adding an image background to it?
Thank you!
One of the many things on my eternal to do list but for sure. MORE caption options are must D: there's simple not enough good ones atm indeed. Someday for sure!
Is there a way to block or prevent engagement with specific users?
I have someone on my stream who keeps grooming my pet to say really dumb things that goes against her personality. I have to reset her memory frequently so that she'll stop being cringe for this user's enjoyment. I don't want to ban the person but it's getting very annoying to deal with it every stream
heya! yeah, on the moderation tab you can add users to be ignored by redeems/the ai. That should do the trick
Thank you!
I can't get VTS pog to start up
heya! thats super werid! You can find a link to our discord server on the main page https://vtspog.com , feel free to make a thread on support there and we can give ya a hand over there to try to make it work. I'm positive we can figure it out if we check it out together ♥
How do I update? I can't seem to find it anywhere
heya! you need to download the new version and just unzip the file and either replace the folder or delete the old one and just use the new one. VTS P.O.G. saves configuration on windows appdata so configs carry over between versions, they are not saved on the vtspog folder..
doesnt seem to run through crossover on mac, window with the program is just non existent with no plugin pop out in vts…
little experience myself in mac development so I wouldnt even know where to start with that, sadly a bit outside of my knowledge as a developer. I'm planning on getting a mac around February (hopefully) to adapt vtspog for mac cause I don't even have one myself and are a bit hard/expensive to get where I live (Argentina)
i would try looking at another vts plugins with mac support for reference
Looking forward to seeing a Linux version!
not a linux user myself, so low experience in adapting it to it BUT one of our users made a guide on how to run it on linux. I wasnt able to try it myself, but seems to be working after many hoops! Let me link the video they made going through their setup here
Thanks for the reply. I'm familiar with Lutris but I don't believe I had tried it for VTS-POG.
I'll give this a shot later and report my findings.
let me know how it goes ♥
Lutris+Proton-GE was the trick!
I was given a free copy to test with some months back that I couldn't get working.
Now that I have this running, I'm buying a copy.
Still would be great to see a native Linux version but this definitely helps!
This the best thing. Thankyou so much for your help and thankyou so much for making this
I want to buy it. But I want to know if can user local llm models
not atm, but ollama support is in the works, so far the most stable option for local llm I have found. If you know coding, you can also send generated responses to vtspog through our local api, but the setup may be a bit complex unless you are confident in your python (given most local llm model solutions run in python)
for the openai stuff why just make the b ase url customizable so we can use lmstudios server
also add support for coqui tts or add support to use use xtts-api-server https://github.com/daswer123/xtts-api-serverThanks I will be wait then ^^
if they use the openai api we the base url can be changed and can run a server with lmstudio that be dope if they can update and use xtts-api-server also
didnt know about lms studio or coqui so i would need to give em a check, but I'm always open to suggestions. Will try giving em a look once I have the time~
is it possible to change the gpt model? i was hoping to use the new 4o mini model
next release! its already available in a test build Im sharing for testing, hit me in the dms on the discord server and I dont mind sharing it ♥
As a vtuber I'm interested in this program, since it looks cool and also interesting way to interact with a chat.And also, I saw the Vnyan integration on twitter.
But do you plan any language update? For example Ukrainian? Unfortunately, not so many TTS working with this language and it's a bit upset.
heya! sadly the vast majority of voices available around are in english, the market is way too focused there. We have in streamelements and azure tts voices in ukranian but only 3 with them added up (and quality tbh cant compare to the english ones). So we have some ukranian voices, just not many D: