Paid Scenes vamX AI Chat - RESPONDS TO TOUCH + GPT4 + NSFW AIs + 100 Personalities + 1000s of Actions - 1.37.1

For a much faster and more accurate chat, use the updated Deepgram App for speech recognition. This recognizes speech without holding down any buttons. There are timing options to help her respond at the right time, when you finish speaking. Download the vamX Deepgram App from https://www.patreon.com/posts/97100910

You can now make your own personality sets using the Deepgram App, see the instructions in the Deepgram App folder after downloading the Deepgram App using the above link.

You can choose which types of vamX Actions may be triggered by the Chat AI. In the vamX Scene -> AI Chat section, check Lock Anims, Lock Look, or Lock Pose. For no Seamless Anims, check Lock Anims (while in a regular pose). For only Seamless Anims, check Lock Pose (and perhaps Lock Scene and Look too).

To have the Male or Threesome person speak as the Chat AI, change "Speak As: Female" to "Speak As: Male" (or 3rd Person) in the new Chat Web UI.

The Seamless Animation Library now loads much quicker and is half the size. The quality of the animations is the same.

For short, fast chat responses change Quick Speech to Very Quick Speech in the Web UI.

There is now a separate Narrator voice which can be set to read the description (non-dialog) parts of chat. For example the Chat AI sometimes generates dialog, but then also adds a description in parenthesis or asterisks. For example you might see "That's a great idea Jack! (Jenny smiles happily)". Now, if you have a Narrator voice set, then the Female would say "That's a great idea Jack", but then a separate voice, that isn't spoken by the female in game, would say "Jenny smiles happily".

Improved AI Chat responses to detected in-game actions (if you touch her, press a vamX button to remove clothes, etc.). Before if she did an action (Emily puts on her shirt) sometimes the AI responded as if Jack told her to put on her shirt, etc. Overall, the AI Chat responses will now be more accurate / make more sense in response to in-game actions.

Switched GPT-4 to GPT-4o. This improves the text responses when using SFW GPT-4o.

Fixed an issue where audio files were sometimes spoken out of order. To speed up speech, her response is sent in multiple parts (e.g. if Quick Speech is set, and she will say a couple of sentences). Sometimes audio from a shorter, later sentence, finished generating first and arrived and played first. Audio is now played in order.

Fixed an issue where pressing Retry Last or generally receiving responses with many audio files could cause disappearing text an errors with future responses. Hopefully this is fully fixed but it may need additional work in the future.

https://www.patreon.com/posts/chat-ai-only-1-1-106667788

AI Chat detection of clothing removal / changes, especially when using the Clothes & Hair tab, or BUILD Female Clothes.

Improved AI Chat detection and responses to using dildos, vibrators and butt plugs on the AI.

The Chat AI can now respond to complex touches. If you touch her (for example in VR, or by loading a pose with the Male active) some touch information will be sent to the Chat AI, and this will become part of the story.

For example, if you touch her arm (and the story has Jack and Emily) you might see in the story "(Jack touches Emily's arm)" and then she might say (in response to your touch) "Oh, that's sweet Jack, hold me tighter".

If you switch to missionary pose (or ANY other man on top pose), you would see "(Jack fuck's Emily's pussy)". These are not pose specific notifications, changing poses simply triggers sending whatever main touch is happening in the new pose to the Chat AI.

There are also notifications sent when using vamX Toys (Other -> Sex Toys) and some Bondage items, like blindfolds, nipple clamps, or chains (Other -> Bondage, Domination and Role Play).

To disable touch notifications for the Chat AI, uncheck the Chat AI -> Send Touch/Events toggle.

Added Lock Scene toggle, and Lock Pose toggle to the vamX AI Chat menu.

You can now stay in the same Scene (environment) while in AI Chat by checking the Lock Scene toggle. This box ignores all AI Chat (and regular voice commands) that would lead to a Scene change. This checkbox is in the Chat AI section in the vamX menu (Scene tab -> Chat AI).

You can now make sure she stays in the current Pose while in AI Chat by checking the Lock Pose toggle. This box ignores all AI Chat (and regular voice commands) that would lead to a Pose or Animation change. This checkbox is in the Chat AI section in the vamX menu (Scene tab -> Chat AI). Minor pose changes from Action -> Start Sex, which allows changing to similar poses, can still happen when this box is checked.

KEY NEW FEATURES​

There are now over 30 NEW "Improved Voices" with better voice quality and emotional tone. The Improved Voices are quicker than ElevenLabs or Verbatik voices, but not as quick as the original built-in Chat AI voices (which have now been renamed to Quick Voices).

ElevenLabs Voices - Requires a paid subscription to ElevenLabs.io and allows you to make voices.
Upgraded ElevenLabs API to v2 (as requested by a few users). This adds support for Chinese, Korean, Dutch, Turkish, Swedish, Indonesian, Filipino, Japanese, Ukrainian, Greek, Czech, Finnish, Romanian, Danish, Bulgarian, Malay, Slovak, Croatian, Classic Arabic and Tamil. ElevenLabs Voice quality may also be improved. ElevenLabs voices no longer disappear if you choose an "I Speak" language that isn't supported by ElevenLabs, so you can try any language with ElevenLabs v2 voices (although only supported languages may be pronounced correctly). ElevenLabs v2 works with the new languages listed above, plus all languages from v1, which are: English, Polish, German, Spanish, French, Italian, Hindi and Portuguese.

Added new vamX AI Chat voice options menu. This menu adds a new AI Chat voice option: AI Chat Voice ONLY. The options are now:
1) NEW - AI Chat Voice ONLY (no vamX breathing or moans). This stops breathing, and most moans, but there are still occasional moans which will be removed in the next build.
2) AI Chat Voice + vamX Breathing (can moan at high arousal, but no orgasm)
3) AI Chat Voice + vamX Voice & Orgasm (this lets you select any vamX voice and she will breathe, moan, orgasm, and talk in that vamX voice in addition to AI Chat dialog). Pressing this goes to the vamX voice / language selection. If you choose a "Moans Only" voice, then there won't be much non AI Chat dialog (although some moans contains short words, and the orgasm moans can also contain words in some voices).

Added Bondage Play Emily and Creative Agreeable Emily chat personalities to the Emily section of the main personality list. Agreeable Emily is a bit boring as she basically only agrees to whatever you say. Creative Agreeable Emily mostly likes what you suggest, but responds in more interesting and realistic ways and voices her own opinion. Bondage Play Emily is more like a girlfriend playing with bondage with you (as opposed to a professional Dominatrix).

Added Police Partner Jenny to the main personality list (which was used to create all dialog in the demo video above).

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.