RPGHQ

• Batch process multiple audio files at once
• Full integration with all ElevenLabs voices and models
• Adjustable voice parameters (stability, similarity boost, style exaggeration)
• Built-in audio playback for both source and converted files
• Real-time credit tracking

Files	Version	Type	Description
ElevenLabs Batch Voice Changer (Windows)	1.3	Main	Extract and open the .exe file

► Old Versions

Files	Version	Type	Description
ElevenLabs Batch Voice Changer (Windows)	1.2.1	Main	Extract and open the .exe file
ElevenLabs Batch Voice Changer (Windows)	1.2	Main	Extract and open the .exe file
ElevenLabs Batch Voice Changer (Windows)	1.1	Main	Extract and open the .exe file
ElevenLabs Batch Voice Changer (Windows)	1.0	Main	Extract and open the .exe file

1. Download the zip file and extract the exe to your preferred location
   • Password to extract the file is the epic gamer slur (all lowercase)
2. Launch the application
   ㅤ
3. Enter your ElevenLabs API key (you can get this from your ElevenLabs account settings)
   • Key will be something like this: sk_8d3a71c4520b60d28af76e41c49d12e735c84a0867d5fd23
4. Click Connect to authenticate and load available voices
   ㅤ
5. Add audio files and select your desired voice settings
   ㅤ
6. Click Start Conversion to begin the batch process

• Linux compatibility?
• Make voice parameters save per model

loregamer wrote: ↑ March 1st, 2025, 08:46

v1.1

---

Added an Audio Format option

v1.2

• Added .wav output format that will work with wwise
• Added .flac output format or autistphiles
• Your last selected voice saved when re-opening
• Voice Model settings will be saved per voice

traxtan wrote: ↑ March 1st, 2025, 22:54

Can't see the voice model settings, 1080p laptop monitor with 125% dpi scaling in Windows. Works if I put it back to 100%

125%


100%

loregamer wrote: ↑ March 1st, 2025, 23:55

Can you try this exe?
https://f.rpghq.org/JMTAcp1cdsjI.zip?n= ... v1.2.1.zip

v1.2.1

traxtan wrote: ↑ March 1st, 2025, 22:54

Can't see the voice model settings, 1080p laptop monitor with 125% dpi scaling in Windows. Works if I put it back to 100%

• Voice Conversion Enhancements
  • Voice Seed Parameter: Add support for the seed parameter to enable deterministic voice generation for consistent results when converting the same audio multiple times.
  • Voice Isolation Pre-processing: Implement the ElevenLabs Audio Isolation API as a pre-processing step to clean up input audio before voice conversion.
  • Clarity Boost: Add support for the clarity boost parameter available in newer ElevenLabs models.
  • Chunking for Large Files: Implement chunking to process longer audio files in segments, improving reliability and potentially reducing processing time.
  • Pronunciation Guide: Add support for pronunciation dictionaries to improve specific word pronunciations.
• Voice Creation and Management
  • Voice Generation from Description: Add the ability to generate custom voices from text descriptions using the Voice Generation API.
  • Voice Cloning from Samples: Allow users to create custom voices by uploading voice samples.
  • Voice Library Management: Add functionality to save, categorize, and manage favorite voices.
• Advanced Processing
  • Timestamps and Word-level Control: Implement support for generating timestamps for each word, enabling more precise audio editing.
  • Streaming Processing: Add streaming support for real-time processing of audio files.
  • Language Detection and Translation: Automatically detect the source language and offer translation options.
  • Batch Processing Optimization: Implement parallel processing for multiple files to speed up batch conversions.
• User Experience
  • Audio Preview: Add the ability to preview how a voice will sound before processing the entire file.
  • Advanced Output Settings: Provide more control over output audio quality, format, and compression.
  • Preset Management: Allow saving and loading of voice conversion presets.
  • Progress Estimation: Implement more accurate progress and time remaining estimates.

traxtan wrote: ↑ March 2nd, 2025, 00:20

Password doesn't work anymore, also I tried installing it via github and I think you broke it.
I tried anaconda with py 3.8 env and my normal 3.12 python install (yes I tried reinstalling the libraries), both didn't work.

So is it a problem on my end or what?
Edit: To clarify the password "epic gamer slur" does not work on v1.2.1, I tried 7zip and winrar.

loregamer wrote: ↑ March 2nd, 2025, 00:25

In terms of PyQt6, I had to do this to get it working. Can copypasta it from the github readme

AuctorLucan wrote: ↑ February 23rd, 2026, 16:27

Hmm... It seems to me the Speaker Boost toggle isn't working? At least when I disable it in the tool, it still generates with Speaker Boost when looking at the log at the site.

The result is also clearly with Speaker Boost.