#3737th of 93 in VoiceFor voice, speech and music

applio

Voice conversion tool with a Gradio UI, training and plugin support

Stars
4k
License
MIT
Last commit
Nov 2026
Last release
Oct 2026
Language
Python
Stars, last 29 weeks+868
25 Apr 2026: 3,162 stars2 May 2026: 3,188 stars9 May 2026: 3,212 stars16 May 2026: 3,244 stars23 May 2026: 3,266 stars30 May 2026: 3,299 stars6 Jun 2026: 3,325 stars13 Jun 2026: 3,351 stars20 Jun 2026: 3,373 stars27 Jun 2026: 3,399 stars4 Jul 2026: 3,427 stars11 Jul 2026: 3,456 stars18 Jul 2026: 3,478 stars25 Jul 2026: 3,500 stars1 Aug 2026: 3,527 stars8 Aug 2026: 3,554 stars15 Aug 2026: 3,584 stars22 Aug 2026: 3,614 stars29 Aug 2026: 3,648 stars5 Sept 2026: 3,675 stars12 Sept 2026: 3,696 stars19 Sept 2026: 3,726 stars26 Sept 2026: 3,751 stars3 Oct 2026: 3,783 stars10 Oct 2026: 3,820 stars17 Oct 2026: 3,856 stars24 Oct 2026: 3,897 stars31 Oct 2026: 3,950 stars7 Nov 2026: 3,997 stars14 Nov 2026: 4,030 stars

3,162 on 25 Apr 20264,030 on 14 Nov 2026

From GitHub's daily star counts.

Checked on GitHub.

Overview

Applio converts the voice in an audio clip to another voice and includes model training with TensorBoard monitoring. It runs locally through install and run scripts for Windows, Linux and macOS, and opens a Gradio interface in the browser. Plugins extend it, and Colab notebooks are provided with and without the UI.

Who it is for: Artists, developers and researchers doing local voice conversion

Strengths

  • Install and run scripts for Windows, Linux and macOS, plus precompiled Windows releases
  • Windows updater keeps models, logs, audio, presets and settings across upgrades
  • Plugin repository, hosted playground and Colab notebooks with and without UI
  • MIT-licensed code and weights, commercial use allowed

Weaknesses

  • Maintainers say updates will be infrequent: security patches, dependencies, occasional features
  • Official version requires accepting a separate Terms of Use in addition to MIT
  • Commercial users are advised to contact maintainers to confirm ethical alignment
  • Updater script is documented only for compiled Windows releases

What it needs

  • Docker + Compose
  • Needs Gradio, TensorBoard

What changed

From the release notes. No flag means the note does not say so, not that the upgrade is safe.

Also in Voice

See all 93
Also in Voice
RankProjectScore
1voicestudioDesktop app for voice cloning, dubbing, dictation and audiobooks113k starsAGPL-3.098 out of 100
2handyOffline push-to-talk dictation app that pastes transcripts into any text field39.1k starsMIT92 out of 100
3whisper.cppC/C++ speech-to-text engine running OpenAI Whisper models locally55.3k starsMIT90 out of 100
#4meetilyDesktop app that records, transcribes and summarizes meetings locally Live demo ↗ (opens in a new tab)32.8k starsMIT87 out of 100
#5buzzOffline desktop app for transcribing and translating audio with Whisper22.9k starsMIT84 out of 100