RepoPicks Radar

Updated every day around 23:30 UTC

Guides

Bark Voice Cloning

KevinWang676/Bark-Voice-CloningReviewed by AI

Checked by RepoPicks Radar on

What is Bark Voice Cloning?

This repository collects ready-to-run voice cloning tools. The main part is a Bark web interface with three tabs: create a voice from an uploaded recording, read text with that voice, and swap the voice in an existing recording. A second interface, Sambert, covers Chinese voice cloning with labelling, training and use. The rest is a list of one-click Colab notebooks for other open models (GPT-SoVITS, XTTS, VALL-E X, F5-TTS, CosyVoice, OpenVoice and more). Running it on your own computer needs Python and, in practice, a graphics card; the notebooks run in the browser on Google's machines.

Bark Voice Cloning is free and open source (MIT) and can replace ElevenLabs, Respeecher, and Kits AI.

How easy is it to install Bark Voice Cloning?

B · installer plus one simple step · Web

  • Windows D
  • macOS D
  • Linux D
  • Web B

The browser route earns the best grade: you open one of the Colab notebooks and run the setup cells, with nothing installed on your computer, though you need a Google account and the session's graphics card. On Windows, macOS and Linux you install Python 3.10 or newer and the requirements by hand, a graphics card is recommended "CPU works but is slow", and the README warns that the "Create Voice" path in app.py still points at the Colab folder /content/... and may need editing.

Bark Voice Cloning on GitHub

Stars
2,944on Nov 10, 2026
Downloads
—all releases
Growth
—no gain in the last reading

Stars over time

2,9442,9452,946 Nov 6Nov 7Nov 8Nov 9Nov 10 2,9442,9452,946 Nov 6Nov 8Nov 10

Facts

Runs on
Windows, macOS, Linux, Web
You need to install
Nothing extra
To build from source
Python, Docker, Graphics card
Disk space
950 MB–4.3 GB · estimate
Accounts or keys
OpenAI (only for the OpenAI TTS notebooks)
Cost
Free · The code is free (MIT); the Colab notebooks use Google's free tier, which limits how long a session with a graphics card lasts
License
MIT (Permissive)
Last change on GitHub
May 31, 2026

Bark Voice Cloning risk signals (7)

  • AttentionDependencies with known vulnerabilities

    Pinned dependencies with known vulnerabilities (OSV): gradio: GHSA-26jh-r8g2-6fpr, GHSA-279j-x4gx-hfrh, GHSA-34rf-p3r3-58x2

    automatic check

  • Attentionvoice cloning impersonation risk

    The interface clones a voice from an uploaded recording and swaps the voice in existing audio; the README also advertises an "AI song cover generator". The repository's own Disclaimer says to "obtain proper consent before cloning or converting any voice"

    AI review

  • Attentiondocker image builds a different project

    The Dockerfile does not use this repository's code: it runs "git clone https://github.com/C0untFloyd/bark-gui", installs that project's requirements and starts its webui.py

    AI review

  • Attentioninstalls binary wheel from personal repository

    requirements.txt on Windows pulls a prebuilt package from a private release page: fairseq@https://github.com/Sharrnah/fairseq/releases/download/v0.12.4/fairseq-0.12.4-cp310-cp310-win_amd64.whl

    AI review

  • Attentionpinned to old versions

    requirements.txt pins gradio==3.33.0 and gradio_client==0.2.7, versions chosen in October 2023 to work around an error, and the checks found known vulnerabilities in that gradio version

    AI review

  • Infohardcoded colab paths in local code

    README, "Important note for local runs": "The default path in app.py is set for Colab (/content/...). If you run locally, you may need to update that destination path"

    AI review

  • Infodownloads models on first run

    README: "On first run, Bark checkpoints are downloaded into ./models/" and "HuBERT + tokenizer for voice cloning are downloaded into ./models/hubert/"

    AI review

Evidence is shown in its original language.

What Radar could not check about Bark Voice Cloning

  • Whether the 2023-era dependencies still install today, on Colab or locally
  • Whether the HuggingFace demos linked in the README are still online
  • Real disk use and video memory after the model files download
  • How close the cloned voice sounds to the original, in English and in Chinese
  • Whether the many third-party notebooks still work, since each depends on another project

Similar projects

The RepoPicks app

Coming soon: install in 1 click with the RepoPicks app.

Before you download

See the release page on GitHub