Download Latest Version Applio 3.6.5 source code.zip (19.2 MB) Google Add to Preferred Sources
Home / 3.6.5
Name Modified Size InfoDownloads / Week
Parent folder
Applio 3.6.5 source code.tar.gz 2026-09-19 19.0 MB
Applio 3.6.5 source code.zip 2026-09-19 19.2 MB
README.md 2026-09-19 2.0 kB
Totals: 3 Items   38.2 MB 75

Important Installation Guidelines

### Before You Install Applio Please review these essential instructions to ensure a smooth installation:

  • File Location: Place the Applio files in a dedicated folder on your C drive.
  • Access Control: Avoid placing Applio in folders that require elevated privileges.
  • Administrator Rights: Do not run the run-install.bat script with administrator privileges.
  • Path Requirements: Ensure the installation path is free of spaces or special characters.
  • Security Settings: Temporarily disable your antivirus and firewall to prevent any issues with missing dependencies during installation. ### Installation Steps
  • Download Compiled Version: Get the zip from this link.
  • Run Applio: Extract the .zip file, then open the run-applio.bat file.

What's New in This Release

  • Added a new CLI with an overhauled command-line inference workflow.
  • Added job lifecycle and batch conversion progress notifications through toast messages.
  • Improved accessibility with screen reader support, clearer control labels, section headings, and friendlier file names.
  • Added an opt-in RMVPE high-register pitch correction system to address octave errors above ~1040 Hz.
  • Improved multi-speaker training and finetuning with a new randomized approach.
  • Enabled TF32 for training and optimized ZLUDA execution for AMD GPUs.
  • Improved audio preprocessing and resampling, including better preservation of audio at the top of files.
  • Updated and expanded localization across the interface.
  • Fixed issues with model blending, batch formant controls, model information, TensorBoard links, CLI inference on AMD, and numerical rounding.
  • Improved Linux compatibility by disabling cuDNN benchmarking in environments such as Kaggle and Colab.

Full Changelog: https://github.com/IAHispano/Applio/compare/3.6.4...3.6.5

Source: README.md, updated 2026-09-19