# IAHispano/Applio

A simple, high-quality voice conversion tool focused on ease of use and performance.

Repository: https://github.com/IAHispano/Applio
Canonical: https://ross.abutalabs.com/products/applio
Homepage: https://applio.org
Language: Python
License: MIT
License Family: permissive
Topics: rvc, vc, vits, voice, ai, voice-cloning, voice-conversion, applio, voice-clone, pytorch, speech, speech-to-speech, text-to-speech, tts
Last push: 2026-08-26T12:04:15+00:00

## Health v2 (maintenance only)
Score: 90/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 83, longevity 80
- inputs: {"age_days": 1122, "days_push": 7, "days_rel": 37, "gap_med": 40, "n_releases_24m": 12}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3644, forks 584 (observed 2026-08-28T04:08:12.842834+00:00)

## What it is
Applio is an open-source, MIT-licensed voice conversion suite built on RVC that lets users convert audio into other voices, train custom voice models, and change voices in real time. It ships with a GUI, plugin system, voice blending, TTS integration, and audio analysis tools, and runs locally on Windows, macOS, and Linux or in the cloud via Colab.

## Use cases
- convert a song into another singer's voice to make AI covers
- train a custom voice model from my own audio dataset
- change my voice live while streaming or on calls
- generate speech from text in a specific voice
- blend two voice models into a new unique voice
- batch convert a folder of audio files to a different voice
- analyze audio files before training a voice model

## When to choose
- you want a beginner-friendly, all-in-one RVC voice conversion tool with a GUI
- you need both offline inference and custom voice model training in one package
- you want low-latency realtime voice changing on a GPU
- you prefer an MIT-licensed, self-hosted alternative with no account or telemetry

## When to avoid
- you need fully offline text-to-speech, since the built-in TTS relies on EdgeTTS online
- you have no GPU and want realtime conversion, which is GPU-only
- you need a programmable API-first pipeline rather than a GUI application
- you require frequent new features, as the project is now in maintenance mode

## Facets
- artifact type: application
- maturity: maintenance
- function: audio-processing, speech-recognition, tts, machine-learning, llm-inference, gui, plugin-system
- domain: machine-learning, artificial-intelligence, media, cross-platform
- platform: windows, python, cross-platform
- tags: voice-conversion, rvc, voice-cloning, ai-covers, realtime-voice-changer, voice-model-training, speech-to-speech, pytorch, gradio-ui, audio, macos, linux, gpu, desktop

## Member repositories
- IAHispano/Applio (main) score 90

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:12.842834+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:31:45.182548+00:00, confidence not recorded.
  - readme: https://github.com/IAHispano/Applio (fetched 2026-08-28T04:08:12.842834+00:00, sha 49ff613190c9)
  - homepage: https://applio.org (fetched 2026-08-29T09:26:19.516320+00:00, sha 7895e1218d21)
  - site_page: https://docs.applio.org (fetched 2026-08-29T09:26:19.519482+00:00, sha 8b230bdb999e)
  - site_page: https://docs.applio.org/getting-started/installation (fetched 2026-08-29T09:26:19.522035+00:00, sha 98bbdff1d620)
  - site_page: https://docs.applio.org/getting-started/inference (fetched 2026-08-29T09:26:19.524302+00:00, sha 7184928c4d88)
  - site_page: https://docs.applio.org/getting-started/realtime (fetched 2026-08-29T09:26:19.526504+00:00, sha 964c4b1879f4)
  - site_page: https://docs.applio.org/getting-started/training (fetched 2026-08-29T09:26:19.528257+00:00, sha 5409fd81a2cc)
  - site_page: https://docs.applio.org/getting-started/voice-blender (fetched 2026-08-29T09:26:19.530094+00:00, sha 1849107c5126)
  - site_page: https://docs.applio.org/getting-started/tts (fetched 2026-08-29T09:26:19.532579+00:00, sha b245ad00172a)
  - site_page: https://docs.applio.org/getting-started/audio-analyzer (fetched 2026-08-29T09:26:19.534884+00:00, sha e88477a77f01)
- Data as of 2026-08-30T08:39:29.467469+00:00.