🎧 The Future of Voice & Sound Design

Hey everyone! 💜

I want to talk about something important and hear your honest opinion about the current sound design and voice work in my videos.

As many of you probably noticed, the visual quality of my animations has improved a lot, but the audio side sometimes doesn’t reach the same level yet.

The main reason is the AI model I currently use — WAN 2.2. This model creates the animation only, without built-in voice, dialogue, or sound. All audio has to be created separately afterwards.

You might ask: "Why not just use another AI model?"

The answer is simple: right now, other models can’t achieve the same results. They usually lose the natural movement, facial emotions, smooth body animation, physics, and overall quality that WAN 2.2 provides.

So for now, I’m choosing the best possible animation quality, even if that means making compromises with voice quality and lip sync.

I’m constantly testing new AI tools, new models, and new ways to improve the sound design. The moment another model can match or beat this quality, I’ll absolutely consider switching.

But for now I want your feedback:What direction would you prefer for future videos?-----------------------------------------------------------------------------------------------------❤️ Option 1 — Keep the current styleKeep voice acting, dirty talk, moans, and character personality as they are now.

Yes, sometimes the voice emotions or lip sync won’t be perfect, but the characters will feel more alive, emotional, and closer to their original personalities.

I also want to mention that creating the voices is a very time-consuming process. I spend a lot of extra time generating voice lines, editing the audio, adjusting timing, and manually matching everything with the animation as closely as possible.

If you feel that the current voice quality doesn’t add enough value to the videos, it might be better to temporarily move away from this approach until better AI voice tools become available. It would also make the editing process much easier and allow me to focus even more on creating new animations.

-----------------------------------------------------------------------------------------------------🔥 Option 2 — Only moans & reactionsRemove dirty talk and dialogue completely.

This means fewer distracting voice problems and no bad lip sync moments, but characters will lose some personality and interaction.

Also, future manga-style collections may lose a big part of their atmosphere without dirty talk and character dialogue. These collections rely much more on emotions, personality, and storytelling — so removing voices could make them feel less alive, even if the animation quality stays the same.

-----------------------------------------------------------------------------------------------------✨ Option 3 — Pure animation experienceRemove all voices, moans, and dirty talk.

Only high-quality animation with background music and atmosphere. Your imagination will do the rest hehe 😏

If you have another idea or suggestion, please write it in the comments! Maybe there is a better solution I haven’t thought about yet.