repowiserepowise

MCP server

debpalash / voicestudio

VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages.

★ 116,157stars on GitHubPythonAGPL-3.0

This connects Repowise to debpalash/voicestudio's code. It does not install voicestudio.

Repowise maps public repos from their source. Not affiliated with debpalash. What is Repowise?

github.com/debpalash/voicestudioIndexed at 4d4cb0b

What is voicestudio?

VoiceStudio is an open-source, fully local AI voice studio for voice cloning, voice design, video dubbing, dictation, transcription and audiobook creation in 646 languages. It takes a clean reference recording and a script, then runs them through cloning, text-to-speech and speech-recognition engines to produce speech in the cloned voice. The project is written mainly in Python, with an Electron desktop shell. To install it, run git clone https://github.com/debpalash/VoiceStudio.git and follow the steps below. Its code health is 7.2 out of 10 (Good), ranked #131 of 4,000+ indexed repos. The last commit to voicestudio was on Oct 29, 2026, and 120 people have contributed.

As of commit 4d4cb0b, indexed Oct 30, 2026. What it is comes from a model reading the README; the rest is measured from the source and git history, not from the maintainer.

For agentsvoicestudio.md

Repo facts: type, license, health, rank, contributors
voicestudio facts
TypeMCP server
LicenseAGPL-3.0
Code health7.2 / 10 (Good)
Health rank#131 of 4,000+ indexed repos
Last commitOct 29, 2026
Contributors120
Bus factor1
Size4,347 files, 558,430 lines

Install voicestudio

Commands copied from the README

  1. 1Clone the repository from GitHub.
    git clone https://github.com/debpalash/VoiceStudio.git
  2. 2Change into the project directory.
    cd VoiceStudio
  3. 3Install the dependencies and launch the app with Electron.
    bun run dev

Releases on GitHub (latest v0.5.8, Nov 12, 2026)

Full install notes on GitHub

Explore voicestudio

Ask about this code in your agent

This connects Repowise to voicestudio's code. It does not install voicestudio. To install voicestudio, use the install steps.

Useful if you want to change or fork voicestudio: your agent can ask how it is put together and get answers that cite its files.

Ask about voicestudio

Answers come from voicestudio's README and source, with the files they cite. Two free answers a day without an account.

Featured answer

VoiceStudio is an open-source, fully local AI voice studio for voice cloning, voice design, video dubbing, dictation, transcription and audiobook creation in 646 languages. It takes a clean reference recording and a script and runs them through cloning, text-to-speech and speech-recognition engines to produce speech in the cloned voice. The project is written mainly in Python with an Electron desktop shell, and the repository holds 4347 files. Requests arrive over HTTP and WebSocket at the backend directory, where each text-to-speech and speech-recognition engine runs in its own process under backend/engines, while backend/core supplies shared services for data storage, settings and user-facing error messages. The electron directory sends requests to that local backend, and the omnivoice directory handles text-to-speech, voice copying, command-line tools and the web demo. To start reading, begin with the backend directory and its core and engines subfolders, then the electron shell, since the Application layer holds 926 files and the Service layer holds 320.

Files per layer in voicestudio10 layers.

Basis: Inferred · knowledge graph· as of 4d4cb0b

Want this for your own codebase? Map your repo free

About this page

Get a page like this for your own codebase

Repowise built this map of debpalash/voicestudio from its source and git history. It parses every symbol, draws the dependency graph, scores each file's health from complexity, duplication, coverage and churn, finds hotspots and owners in the history, and writes documentation for every module. Your coding agent reads the same index over MCP, so its answers cite real files.

Free for 2 public repos, with a page like this one. No card. See how Repowise works

Prefer local? pip install repowise && repowise init indexes your own checkout, no account needed. Star Repowise on GitHub

debpalash/voicestudio FAQ

What is VoiceStudio?

VoiceStudio is an open-source, fully local AI voice studio for cloning and designing voices and dubbing videos. It also covers dictation, transcription and audiobook creation in 646 languages.

How does VoiceStudio work?

VoiceStudio takes a clean reference recording and a script, then runs them through cloning, TTS and ASR engines in its backend. It produces rendered audio and dubbed tracks that the desktop, mobile and CLI surfaces play back and export.

How do I install VoiceStudio?

VoiceStudio can be run from source by cloning the repository and running bun run dev. That command installs the JavaScript dependencies and, for a supported local backend, the Python dependencies before launching Electron. See the install steps

What language is VoiceStudio written in?

VoiceStudio is written mainly in Python. TypeScript, JavaScript, Kotlin and Swift files also make up parts of its code.

How is the VoiceStudio code organized?

VoiceStudio is split into modules such as backend, which handles HTTP and WebSocket requests and speech engines, and electron, which provides the desktop shell. The omnivoice module handles text-to-speech and command-line tools.

Who is VoiceStudio for?

VoiceStudio is for people who want to clone, design, dub, dictate, transcribe and narrate speech on their own device. It runs on laptops, desktops, servers, phones and tablets.

What license does VoiceStudio use?

VoiceStudio uses the AGPL-3.0 license. Model weights, voices and generated output are treated as separately licensed material, so cloning a voice requires its owner's permission.

Code health

7.2out of 10Good

Hotspots average 5.7, the place fixes pay off most.

On the leaderboards:#32 of 71 Python repos

Key features of voicestudio

  • Turns a clean reference recording into speech in a familiar voice.
  • Translates and dubs videos with speech timed to the original.
  • Describes a voice in words and generates it.
  • Lets you choose your engines and download only the models you need.
  • Offers a floating dictation widget and local transcription.

How debpalash/voicestudio works

Requests arrive over HTTP and WebSocket at the backend directory, which turns them into transcripts, speech and stored project data. Each text-to-speech and speech-recognition engine runs in its own process under backend/engines, so the main application sends text or audio in and gets synthesized audio or a transcript back. backend/core provides shared services that decide where data and settings live, keep secrets out of diagnostic reports and turn failures into messages a user can act on. The electron directory is the desktop shell, which sends requests to the local backend and stays usable when the backend is slow or unreachable. The omnivoice directory turns written text into speech, can copy the voice of a short reference clip, and holds the command-line tools and web demo. The scripts directory contains the command-line tools that maintainers run around releases, store listings and local setup.

The codebase has 4,347 files and 36,385 symbols in 13 modules, led by Python, TypeScript and JavaScript. Code health is 7.2 out of 10, rated good.