11st of 18 in Voice

voicestudio

Desktop app for voice cloning, dubbing and dictation with local speech models

Stars
66.4k
License
AGPL-3.0
Last commit
Oct 2026
Last release
Sep 2026
Language
Python
Stars, last 27 weeks+66,436
8 Apr 2026: 0 stars15 Apr 2026: 98 stars22 Apr 2026: 389 stars29 Apr 2026: 431 stars6 May 2026: 454 stars13 May 2026: 797 stars20 May 2026: 3,569 stars27 May 2026: 4,799 stars3 Jun 2026: 5,884 stars10 Jun 2026: 6,617 stars17 Jun 2026: 6,981 stars24 Jun 2026: 7,385 stars1 Jul 2026: 7,617 stars8 Jul 2026: 7,915 stars15 Jul 2026: 8,304 stars22 Jul 2026: 8,712 stars29 Jul 2026: 9,106 stars5 Aug 2026: 9,408 stars12 Aug 2026: 9,729 stars19 Aug 2026: 10,420 stars26 Aug 2026: 11,612 stars2 Sept 2026: 15,065 stars9 Sept 2026: 21,707 stars16 Sept 2026: 31,805 stars23 Sept 2026: 34,689 stars30 Sept 2026: 50,490 stars7 Oct 2026: 54,686 stars14 Oct 2026: 66,436 stars

0 on 8 Apr 202666,436 on 14 Oct 2026

From GitHub's daily star counts.

Checked on GitHub.

Overview

VoiceStudio is an Electron desktop app with a Python backend for voice cloning, text-described voice design, timed video dubbing, dictation, transcription and audiobook creation. The default engine is k2-fsa/OmniVoice, with other engines selectable and models installed through a Model Manager. It also exposes a local API and an MCP server for agents.

Who it is for: Creators and self-hosters who want local voice cloning, dubbing and dictation

Strengths

  • Covers cloning, voice design, dubbing, dictation and audiobooks in one app
  • CUDA on NVIDIA, Metal on Apple Silicon, and a CPU fallback
  • Local API and MCP for agents, plus watch folders and reusable recipes
  • Installers for macOS, Windows and Linux, plus Docker

Weaknesses

  • AGPL-3.0 app licence; model weights and voices carry separate terms
  • CPU-only use is slower; CPU PyTorch setup needs about 5 GB disk
  • Intel Mac runs the UI only and needs a remote backend
  • Windows on ARM is experimental and CPU only

What it needs

  • GPU optional
  • Docker + Compose
  • Needs Electron, Python, PyTorch, Bun (source build), Node.js 22+ (source build)
  • Models: k2-fsa/OmniVoice

Head to head

Also in Voice

See all 18
Also in Voice
RankProjectScore
2whisper.cppC/C++ port of OpenAI Whisper for local speech-to-text transcription54.4k starsMIT74 out of 100
3VoiceboxLocal voice studio for cloning, TTS, dictation and agent speech57.5k starsMIT69 out of 100
#4Speech-to-SpeechModular voice-agent pipeline exposed through the OpenAI Realtime API13.5k starsApache-2.064 out of 100
#5Kokoro-FastAPIOpenAI-compatible text-to-speech server for the Kokoro-82M model Live demo ↗ (opens in a new tab)5.6k starsApache-2.064 out of 100
#6meetilyDesktop app that records, transcribes and summarizes meetings locally Live demo ↗ (opens in a new tab)31.7k starsMIT63 out of 100