Skip to content
HUIAHUB

debpalash/VoiceStudio

VoiceStudio

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

Metrics updated Trending+16.0% 7d
View on GitHub (opens in a new tab)Homepage / demo

GitHub metrics

Stars
61K
+8.4K this week
Forks
6.8K
30-day growth
—
Open issues
54
53K57K61KOct 4, 2026Oct 13, 2026
GitHub stars from the official GitHub API, recorded each time the repository was checked (3 days).
GitHub stars by day
DayGitHub stars
2026-10-0452589
2026-10-1056746
2026-10-1361023

What it does

VoiceStudio is a desktop app that runs speech AI on your own computer: it clones and designs voices, generates speech from text, dubs videos, transcribes audio and has a dictation widget.

The app is built on Electron with a Python backend. Its default speech engine is k2-fsa's OmniVoice, and the feature catalog lists more than a dozen alternatives, among them CosyVoice 3, KittenTTS, MLX-Audio and IndexTTS 2.5. Transcription defaults to WhisperX, with Faster-Whisper, Parakeet, Moonshine and others available. Models are downloaded when a workspace first needs them. The project says its tools cover 646 languages, a figure that also appears in the transcription tool of its MCP docs.

Beyond the desktop workspaces, VoiceStudio exposes a local API and an MCP server on port 3900, so coding agents can generate speech, clone a voice or transcribe a file. The README states that local workflows stay on your hardware, remote workers are optional and usage analytics only run with consent. Version 0.5.3 was the last release built on Tauri; current releases are Electron only, and Tauri users have to install the new app separately.

Why it matters

VoiceStudio puts cloning, dubbing, transcription and audiobook work into one app that runs on your own hardware, with open models you can swap, and the project pitches it as a self-run alternative to ElevenLabs. Recordings and generated audio can stay on your machine. The MCP server is a practical addition: an agent can call the same voices and transcription you use in the app without a cloud account.

Main features

  • Voice cloning from a reference recording and voice design from a text description
  • Video dubbing with timed speech, plus stories, audiobooks and batch jobs
  • Floating dictation widget and transcription with WhisperX by default
  • Multiple swappable engines, including OmniVoice, CosyVoice 3, KittenTTS and IndexTTS 2.5
  • Local API and MCP server with tools for speech, cloning and transcription
  • CUDA acceleration on NVIDIA and Metal (MPS) on Apple Silicon; CPU fallback
  • Installers for macOS, Windows and Linux, plus a Docker guide
  • Optional remote workers and a model manager for local downloads

Who it's for

  • Creators who want voice cloning, dubbing or audiobook narration without a hosted service
  • Developers who want local text-to-speech and transcription callable over an API or MCP
  • Users with an NVIDIA GPU or Apple Silicon Mac who want to run speech models locally
  • People comparing open TTS and speech-recognition engines in one interface

Strengths

  • Speech generation, cloning, dubbing and transcription in one local app
  • Engine choice is open, with several TTS and speech-recognition backends
  • Agents can use it over MCP and a local API
  • Runs on CPU-only machines as well as CUDA and Apple Silicon GPUs

Limitations

  • Intel Macs get the app interface only and must connect to a remote backend
  • Windows on ARM support is experimental, CPU only and still pending validation
  • The speech models carry their own licences, which the README says to check before commercial use
  • Tauri builds ended at 0.5.3; earlier users must migrate to the Electron app by hand

Getting started

A shell script installs the latest Electron release on macOS or Linux; Windows users can run the PowerShell installer or download an .exe from Releases. Building from source uses Bun.

curl -fsSL https://voicestudio.sh/install | sh

# from a clone of the repository
bun install
bun run setup:api
bun run dev

Requirements: macOS, Windows or Linux; an NVIDIA GPU or Apple Silicon for acceleration (CPU works but is slower and needs about 5 GB free disk); curl and a SHA-256 tool for the installer; Git, Node.js 22+, Bun and Rust to build from source.

Always follow the official instructions in the README on GitHub. This overview is our summary, not a copy.

Sources