Hello!

First of all, thank you for your incredible addon! It works perfectly and adds so much immersion to the game.

I have a couple of questions:

1. I’d like to understand how the voice system works in the addon. Does it use the voices provided by Windows through SAPI, or is it connected to the in-game text-to-speech system built into World of Warcraft? To me, the voices sound similar, and I want to make sure whether the addon relies on WoW’s built-in functionality or not.

2. I want to add new voices for the dialogue system, which I can purchase, such as voices from platforms like IVONA, Acapela, or other TTS services. However, it’s important for me that these voices support the Russian language, as I’m planning to use them to narrate Russian text in the game.

Could you please guide me on how to integrate these voices into the addon? What files or parts of the code would need modification to make this work?

I would be happy to pay for your assistance, as I truly want to enhance my game experience even further. If it’s more convenient for you, feel free to contact me on Telegram: @frostbool.

Once again, thank you so much for your amazing work and this wonderful addon!

Hello and thank you!

You'll need to install the third-party software below so that WoW can discover these voices.

NaturalVoiceSAPIAdapter

I’m incredibly grateful for your help! Everything worked out perfectly, and thanks to you, my immersion in the game will be at 200%!
Thank you so much for your amazing work and for taking the time to assist me. You’re awesome!

Thanks 💯

I’d also like to add that the current voice "Irina" from Windows, which is used for Russian text-to-speech, sounds too formal and doesn’t quite fit the atmosphere of World of Warcraft.

I’ve found a couple of other voices that sound more natural for this type of game. I’d love to add both a female and a male voice to match the respective characters.

However, I’m not a developer and don’t know Lua, so it’s challenging for me to understand how to implement this. It would be great to get your recommendations to make these adjustments to the addon.

One more question: is it possible to integrate neural voices (e.g., using TTS services like ElevenLabs)? This could simplify the process and make it easier to generate new lines without relying on pre-made audio files.

Thank you again for your help!