CHIM XTTS included in the Distro behaves a bit differently from other TTS services…
CHIM XTTS provided in the DwemerDistro comes with no AI voice files! (Well, just one for the narrator…)
Instead, when using CHIM XTTS, the NPC's AI voice will be generated automatically ingame!
When an AI NPC is activated, the plugin will search for compatible audio files within the Skyrim data folder.
Default/Vanilla voicetype = “It just works”
Custom voicetype = Mustensure to engage in conversation before activating them! Longer sentences spoken by the NPC will help achieve more accurate voice generation.
These audio files will be sent to the CHIM XTTS server in the DwemerDistro for generation and cached in the CHIM server under data/voices.
A generated voiceid will be created based on their ingame voicetype. This can be changed to be based on name.
This voiceid is attached to the NPC’s profile in the configuration wizard.
You can still override voices manually, the automatic in-game generation won’t overwrite voices.
If you set everything up correctly, you will be easily able to talk to ANY NPC (with an ingame voice) without any prior setup required! There is currently no way to easily delete voices in the interface. We are looking to fix that.
You can also manually upload .wav files for generation under Configuration - CHIM XTTS Management.
Run the program and leave it running in the background.
Ensure TTSFUNCTION is set to xtts-fastapi for all profiles.
Open windows CMD prompt and enter ipconfig and find your PC’s IP address.
In the default profile use that IP address as the endpoint URL.
Ensure that voicelogic is set to voicetype.
For the default profile only change the voiceid to a valid Mantella XTTS one. This is so the narrator will have a voice.
Click save, and if you have not already click “Copy to All Profiles” to apply the changes to other profiles if they have been created.
That is all you need to do! We would recommend that you do a TTS Troubleshooting test before trying ingame. If you have issues it may be your firewall or your internal windows network.
Whatever voices are in your voice cache, will be used to generate an AI voice every-time it makes an TTS request. You do not need to sync any voices on startup. Using the XTTS Management upload feature will place any new voices into your cache.
If playing normally most voices for NPCs should be in your cache already. You can manually upload new voices using the CHIM XTTS Management page to place new voices in your voice cache.
There is not too much for us to say about the xVASynth implementation. It's a decent TTS service that's been around for a few years now and is simple to install. However it does lack some voices compared to MeloTTS or CHIM XTTS.
Go into the settings menu for xVASynth and modify it to use your GPU.
Install all the voicetypes you downloaded into xVASynth.
In the CHIM Server under the default profile Configuration Wizard set TTSFUNCTION to “xvasynth” and change your IP to your computer’s IP address
TTSFUNCTION set to “xvasynth”. Click Copy to All Profiles if you want all NPCs to use this voice.
For example using “ipconfig” in the CMD prompt I can see my PC’s IP is 192.168.40.20, so I set that for the TTS XVASYNTH url. If you have issues it may be your firewall or your internal windows network.
Click SAVE
If you already have profiles created make sure to use “Copy to All Profiles” to change pre-existing AI NPC’s to use xVASynth.
All new profiles created will now force the AI NPC’s to use xVASynth for their voices, if you have their voice model installed.
MeloTTS is one of our recommended TTS services for you to use. It is free, runs locally, and with a low hardware requirement. Currently we have all the default approved Skyrim Voices trained using it. The quality is not as good compared to CHIM XTTS, but it will allow all players to have easy access to a comprehensive TTS service. There is no current way to easily train more voices using the Distro.
It is rather easy to set up. It can be installed using the main installation script or as an optional component folder in the Distro. You can run it on CPU (required usage for AMD users), or GPU (which is faster). After that just select it as the TTS service in the default profile, and speak to any vanilla NPC. They will automatically be allocated with an appropriate voice whenever they are activated.
We do recommend that you use CHIM XTTS if you have the hardware to do so as it is much better quality.
Here is a guide to run it on the cloud (down below in this document): CHIM Manual
The reason we have MeloTTS support is for users who can not run other more powerful TTS services while supporting all Skyrim like voices.
All our current MeloTTS voices are listed at the bottom of this document.