# voice-cloning-app/Voice-Cloning-App

A Python/Pytorch app for easily synthesising human voices

Repository: https://github.com/voice-cloning-app/Voice-Cloning-App
Canonical: https://ross.abutalabs.com/products/voice-cloning-app
Language: Python
License: BSD-3-Clause
License Family: permissive
Topics: python, tts, text-to-speech, pytorch, deep-learning, voice-cloning, tacotron2
Last push: 2024-12-02T03:42:25+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 2002, "days_push": 639, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1440, forks 238 (observed 2026-08-28T04:04:44.249363+00:00)

## What it is
A Python/PyTorch desktop application for cloning and synthesizing human voices from audio datasets. It handles the full pipeline from automatic dataset generation to training Tacotron2-based models and synthesizing speech.

## Use cases
- clone a voice from audio recordings
- train a custom text-to-speech model
- generate speech in a specific person's voice
- build a TTS dataset from audiobooks or subtitles
- synthesize speech locally on my GPU
- create an AI voice for a project

## When to choose
- you want an end-to-end GUI app for voice cloning rather than assembling training scripts yourself
- you need automatic dataset generation from audiobooks or subtitled media
- you want local training with start/stop control and multi-GPU support on Windows or Ubuntu with an NVIDIA GPU

## When to avoid
- you need production-grade, low-latency TTS inference at scale
- you have an AMD GPU or no NVIDIA GPU and cannot train on CPU or Colab
- you need a lightweight library to embed TTS in another application rather than a standalone app

## Facets
- artifact type: application
- maturity: active
- function: tts, machine-learning, deep-learning, audio-processing, speech-recognition
- domain: speech-processing, machine-learning, deep-learning
- platform: windows, python
- tags: voice-cloning, tacotron2, pytorch, text-to-speech, dataset-generation, model-training, audio, linux, gpu, desktop

## Member repositories
- voice-cloning-app/Voice-Cloning-App (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:44.249363+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 2026-08-30T04:36:33.736394+00:00, confidence not recorded.
  - readme: https://github.com/voice-cloning-app/Voice-Cloning-App (fetched 2026-08-28T04:04:44.249363+00:00, sha d11cbe03c9cb)
- Data as of 2026-08-30T08:39:29.467469+00:00.