WOKADA Voice Changer — How to Stop Choppy/Stuttering Voice Output?

[hazy bane]

Hey everyone,

I installed the WOKADA Voice Changer a few days ago. You can see my current settings in the screenshot.

Problem: My voice consistently sounds choppy/stuttery (see clip).
Setup: I’ve attached a screenshot with my PC specs. If you need more details, just let me know.

Question: Does anyone know how to make the voice in WOKADA Voice Changer stop sounding choppy? Thanks in advance! 🙏

i watched a few videos about it on youtube and got the program and the settings from there as well. can someone help me?

[mild swallow]

That might be caused by a glitch.
There exists a bug that happens when you set the chunk size or extra values. To fix it, you need to switch your processor to CPU and then back to GPU0 after doing that.
You might want to try the things written in this guide: https://docs.aihub.gg/realtime-voice-changer/local/tg-develops-w-okada-fork/

[hazy bane]

I’ve noticed that all the YouTube tutorials are outdated and that there are already many new versions of the Okada client. Can someone help me with what I need to download and what the best settings are?

[mild swallow]

!howtoask

[umbral wigeon]

❓ How to Ask for Help

✅ Before You Ask!

1. Check Docs & Guides: Your answer may already be in the AI Hub Docs or the https://discord.com/channels/1159260121998827560/1159513888199540817 channel.
2. Search the https://discord.com/channels/1159260121998827560/1192011222023950368 : Look for existing posts that solve your issue. Do not invade someone else's post.

📝 How to ask?

Tell your:

• Full GPU Name: (e.g., NVIDIA RTX 4060 8gb vram desktop)
• Operating System: (e.g., Windows 11)
• Detailed Description: What were you trying to do and what went wrong?
• Tutorial Used: Link to the guide you were following.
• Screenshot: A picture of the full error message.

🚫 Prohibited Topics (We Will NOT Help With These)

To maintain a legal, safe & ethical community, we will NOT provide help for:

• ANY illegal activities.
• NSFW/Porn.
  Requests for these topics may be ignored, not helped and result in moderation action.

<:matsuripray:1159685390156967936> Community Expectations

• Be Polite & Patient: Our helpers are volunteers. You may ping the Helpers role once.
• English Only: Please keep all conversations in English.
• Don't Ask To Ask.

[mild swallow]

People would need to know what you have (your pc's specifications)

[ivory bridge]

For AMD Radeon RX 6900 XT GPU, try Tg Develop's W-Okada fork (b2397). https://github.com/tg-develop/voice-changer/releases/download/b2397/voice-changer-windows-amd64-dml.zip The original W-Okada version in your screenshot, especially its DirectML variant, is very buggy for Intel/AMD GPU.

[mild swallow]

If you're willing to use tg-develop's fork instead, then most optimized:
If you're not using the index file: set the chunk size 80ms.
If you're going to use it, set index to 240ms (it might need to be set higher if you have a large model)
Set extra 2.7
Go to advanced settings, and set the following:
protocol: rest, crossfade 0.15, force FP32 activated
download crepe-tiny(onnx)
Exit, then set your pitch extractor to crepe tiny (onnx)
swap processor unit to cpu, then swap it back to your AMD GPU (RX 6900XT) -- this will fix a bug.
For audio settings: Choose server mode: set samplerate to 48000hz, pick wasapi as audio driver.
Set output volume to 180%
set your mic as input. Cable Input as output; monitor driver wasapi as well, and whatever you want to listen to it with.
Open up task manager, go to the details tab and find audiodg.exe there.
set the audiodg.exe priority to High.
set audioidg.exe's affinity to only Processor 2 (disable the other ones)
These settings should work for you for most rvc models