# jianchang512/clone-voice

A sound cloning tool with a web interface, using your voice or any sound to record audio / 一个带web界面的声音克隆工具，使用你的音色或任意声音来录制音频

Repository: https://github.com/jianchang512/clone-voice
Canonical: https://ross.abutalabs.com/products/clone-voice
Homepage: https://pyvideotrans.com
Language: Python
License: NOASSERTION
License Family: other
Topics: clonevoice, tts, voice-assistant, speech-analysis, sts
Archived: true
Last push: 2025-08-29T01:53:41+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 39, release rhythm 8, longevity 72
- inputs: {"age_days": 1018, "days_push": 370, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: archived, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 8989, forks 984 (observed 2026-08-28T04:10:26.670382+00:00)

## What it is
A voice cloning tool with a web interface built on the coqui.ai xtts_v2 model, letting users synthesize speech in any voice from text or convert one voice into another. It supports 16 languages, microphone recording, and optional CUDA acceleration, with a precompiled Windows build for easy use.

## Use cases
- clone my voice to read text aloud
- convert text to speech using a specific voice sample
- change one audio recording to sound like another voice
- record my voice from the browser and use it for TTS
- generate dubbed audio in 16 languages from a script
- convert srt subtitle text into spoken audio

## When to choose
- you want a simple point-and-click voice cloning tool without GPU requirements
- you need multilingual text-to-speech with a custom or cloned voice
- you want to run voice conversion locally with a precompiled Windows binary
- you need to record a 5-20 second voice sample and synthesize speech from it

## When to avoid
- you need production-grade Chinese synthesis quality (English works best, Chinese is mediocre)
- you require a permissively licensed model - xtts_v2 uses the Coqui Public Model License
- you cannot provide a stable proxy for downloading large models from Hugging Face
- you need real-time streaming TTS or API-first integration rather than a web UI

## Facets
- artifact type: application
- maturity: active
- function: tts, speech-recognition, audio-processing, machine-learning, gui
- domain: speech-processing, artificial-intelligence, media
- platform: windows, python, cross-platform
- tags: voice-cloning, xtts-v2, speech-synthesis, voice-conversion, web-ui, cuda-acceleration, multilingual, audio, linux, macos, gpu

## Member repositories
- jianchang512/clone-voice (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:26.670382+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 2026-08-29T17:24:22.842875+00:00, confidence not recorded.
  - readme: https://github.com/jianchang512/clone-voice (fetched 2026-08-28T04:10:26.670382+00:00, sha 21aad495738e)
  - homepage: https://pyvideotrans.com (fetched 2026-08-29T08:24:24.293648+00:00, sha ea83000fc034)
- Data as of 2026-08-30T08:39:29.467469+00:00.