Paid Scenes vamX AI Chat - RESPONDS TO TOUCH + GPT4 + NSFW AIs + 100 Personalities + 1000s of Actions - 1.42

KEY NEW FEATURES​

See the Documentation of ALL CHAT PHRASES which can trigger AI Chat Actions.

Improved Chat AI Action detection accuracy. This means she won't trigger many random vamX actions based on what you say / what she says. You can also set the Actions drop down to Exact Actions. See the first three items in ADDITIONAL FEATURES below.

Chat AI Actions include the entire Seamless Animation Library.

Chat AI Actions include the new vamX 1.36 Scenes / Hub Pack Scenes.

Added regular (non AI Chat) vamX voice commands for the New Scenes / Hub Pack Scenes. You can say "Let's go to the ", "Come with me to the " or "Let's have sex in the " and then say the name of the Scene to open that scene. For example for Oeshii House in the Trees you can say "Let's go to the House in the Trees".

GPT-4
SFW ChatGPT-4 has been added as a model. This is more expensive than GPT 3.5 (which we were using). If we get flooded with use, we may need to ask people to use their own GPT-4 API keys, but we are going to try just offering it for free with the service and see how it goes. This is the latest GPT-4 model which has knowledge of events through April 2023 (previous GPT 3.5 and 4 model data was only through 2021).

Continue
You can now press Continue to have the AI continue talking. If the AI is in the middle of a story, or telling you what to do, and you want to hear more, you can press Continue to have the AI continue without you having to ask "tell me more" or "what next" or anything else. The Continue button is next to Send/Reset/Retry (on the AI Chat page where you can type a message to the AI from vamX).

Kobold AI Refresh
There is now a refresh button by the Kobold AI model list. This way you can press Refresh to see if the available models have changed.

What's Next
More voices, animation, emotional expressions, quicker responses, and other improvements will be released as soon as we finish them

"The future is NOW! amazing work" - vamX Patreon comment on the latest update

This AI solution is fully hosted, so it works out of the box. Setup time after download should take about 5 minutes.

​

New Voices for Chat AI​

We now have a Verbatik voice subscription included. We have a large (but limited) monthly voice generation supply, that greatly expands the number of voices you can choose.

These Verbatik voices include MANY voices in non-English languages, so you can finally talk and get responses in almost any language. This is limited by what languages the Chat AI can handle, so try different Chat AIs if NSFW Ooba doesn't handle your language.

This is also a fun way to get cool accents. Just continue to speak in English, but set the voice to Spanish, Dutch, Italian, or whatever, to have them try to speak English using that voice, for a cool accent.

New Chat AIs​

Ooba II has been replaced with a better model (this was done around a week ago).

Chat models (LLMs) are defined by their parameter size. Large models can have more complex responses as they have more data to generate their responses from. NSFW Ooba and Ooba II are 13B (13 billion parameter) models.

We've now added a 70B (70 billion parameter) model (you can select "Ooba 70B" from the NSFW Ooba drop down). The 70B model is slower to generate responses, but may give better results (not always though).

If NSFW Ooba isn't giving you the conversation you want, try Ooba II, Ooba 70B, or any Kobold Horde model.

You can now also use chat models through Kobold Horde. This means additional possible responses / Chat AIs based on the Kobold cloud hosted AIs (anyone can host any model, and anyone else can use it). Kobold Horde is slow, and even though vamX has priority access to Kobold Horde, you should expect to wait longer for responses (at least 7-10 seconds before the text response) when using the Horde.

When choosing Kobold Horde, by default, it selects a Kobold Horde model that we are hosting. That one will generally be the fastest, but you can also select any Kobold Horde model available on the Horde (although we limit the models we display to those that would return a response within 30 seconds max).

Finally, if you want to host your own model, for lightning fast access to whatever LLM you want, you can now use your own hosted LLMs instead of NSFW Ooba. This isn't a local solution, your LLM still connects with our action generation, voice generation, and vamX connections, but this way if you want to have a fast, exclusive, 70B model of your choice, you can host this on RunPod. We try to make this easy, but this is still an advanced feature for those who want to learn about LLMs. Read the instructions here. If you are a super advanced user you can host somewhere else, but we will only support / help people get things running on RunPod.

CHAT AI IMPROVEMENTS​

Added Ooba II option. Ooba II is an unrestricted/NSFW chat AI. Ooba II isn't smarter, rather it has different strengths/weaknesses/responses. If you don't like the answer you are getting, switch between Ooba and Ooba II, then click Retry Last. We will continue to research various AI Chat options.

Greatly improved accuracy of the action detection system. Her vamX Actions, that are triggered in response to the conversation, should now be more accurate (especially the most commonly used ones like dancing, stripping, getting naked, kissing, some common sex positions, etc.).

To prevent speech from being cut off, actions (like changing clothes) now happen after she finishes talking, not during speech. Actions also happen in order, not simultaneously, so if she suggests two things, the first one happens, then the second.

Improved animations loaded for dancing and stripping.

Fixed click at beginning of ElevenLabs played audio. Improved speed of ElevenLabs responses. There were multiple reports of ElevenLabs audio stopping working (the reported fix was to switch to a non-ElevenLabs voice and back). I haven't been able to reproduce this error, but hopefully these fixes have also solved that issue.

Improved output text to reduce the occurrence of unspeakable text, like fffuuuucccckkkk or ABCCDFDJFDKSHDF during orgasm. This may/will still occur. If it does you may be able to get around it by changing the personality text at the top, for example instructing the AI what to say to express pleasure, etc. Switching to Ooba II may or may not help.

Lowered volume of non-AI moans and speech when combining with AI Chat. This stops breathing from being super loud in comparison with Chat AI audio.

You are now notified if you use up your ElevenLabs quota.

Fixed issue where if you saved an AI Chat scene, and loaded it, it didn't automatically initialize the AI Chat on scene load.