Who is VoiceStudio for?

Creators, developers and students who want speech tools running locally; no coding is needed for the desktop app, but a GPU helps and you should only clone voices you have permission to use.

What can you build with VoiceStudio?

Clone your own voice from a short recording to narrate videos or podcasts. Dub a video into another language with speech timed to the original. Turn a book or long text into an audiobook on your own computer. Dictate text anywhere using the floating widget. Connect a coding agent to the local API or MCP server to generate speech from scripts.

AI-generated illustration

debpalash /

VoiceStudio

Desktop app for cloning voices, dubbing video and dictating, run on your own machine

81.9k stars
29.9k stars since 3 Oct
Python
Updated today
Beginner friendly
Image, video & audio

Open on GitHub (opens in a new tab) Website (opens in a new tab)

VoiceStudio puts several speech tasks in one app: text to speech, voice cloning, voice design, video dubbing, dictation, transcription and audiobook creation. The project says it covers 646 languages. The default engine is k2-fsa/OmniVoice, and you can switch to other engines listed in the feature catalog.

Most work runs on your own computer. It uses NVIDIA CUDA on Windows and Linux, Apple Silicon acceleration on Macs, and falls back to the CPU on machines without a GPU, which is slower. Remote workers and services are optional, and usage analytics only turn on with your consent.

It positions itself as a local, open-source alternative to ElevenLabs. It also offers a local API and an MCP server so coding agents and other programs can call it. The code is AGPL-3.0, and each model has its own license, so check them before commercial use.

What it does

Voice cloning and design
Clone a voice from a clean reference recording, or describe a voice and have one designed for you.
Video dubbing
Dub videos with timed speech, so the new audio lines up with the original.
Dictation and transcription
A floating widget handles dictation, and the app can also transcribe audio.
Stories, audiobooks and batch jobs
Produce longer spoken content and run jobs in batches.
Local API and MCP for agents
Other tools and coding agents can use VoiceStudio through a local API and an MCP server. An agent skill can be added with npx.

What you could build

Clone your own voice from a short recording to narrate videos or podcasts.
Dub a video into another language with speech timed to the original.
Turn a book or long text into an audiobook on your own computer.
Dictate text anywhere using the floating widget.
Connect a coding agent to the local API or MCP server to generate speech from scripts.

Get started

Run the installer for your system (the second command is for Windows PowerShell), or download a build from the Releases page. Open Voice cloning, choose a voice or add a clean reference recording, type your text, install the model when prompted, and generate.

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

irm https://voicestudio.sh/install | iex

Commands are copied from the project's README. Read it on GitHub for the full setup.