R_REDDYX.XYZ
VoicePython★ 110,614⑂ 12,250 forksAGPL-3.0

debpalash/VoiceStudio

LOCAL AI VOICE STUDIO WITH CLONING AND DUBBING

Open-source cross-platform tool for voice cloning, video dubbing, and audiobook creation in 646 languages. Runs fully locally without cloud APIs or registration.

// KEY FEATURES

  • Voice cloning from reference recording and speech generation in 646 languages
  • Video dubbing with speech synchronization to original timing
  • Voice design from text description and local models via Model Manager
  • Dictation, transcription, and batch audiobook creation with local API

// DEEP DIVE: HOW IT WORKS

VoiceStudio is a desktop Python application with a web interface that unifies multiple TTS and ASR engines into a single workspace. The default engine is OmniVoice (k2-fsa), while Model Manager connects dozens of other models — CosyVoice, XTTS, Whisper, etc. All computation runs on user hardware: GPU (CUDA, Metal, Vulkan, ROCm) or CPU, with models downloaded on demand.

Unlike ElevenLabs and cloud alternatives, the project requires no account, internet during operation, or data leaving the device. The AGPL-3.0 license permits commercial use of the free version. The paid Pro build adds closed-source code, a client-work license, distributed rendering across multiple GPUs, and priority updates. A Cloud API is planned for users without GPUs.

Supported platforms: macOS 13.3+ on Apple Silicon (Metal/MPS), Windows with NVIDIA CUDA and experimental ROCm for AMD RDNA 2 (RX 6000 except 6500 XT), Linux. GGUF engines have Vulkan acceleration on AMD, Intel, NVIDIA. Installation via Homebrew, DMG, or native builds. Requirements: Python environment, several GB disk space for models, GPU optional but accelerates workloads.

// USE CASES

Best for: Content creators, localizers, and voice application developers

  • Dub video into another language preserving speaker voice and timing
  • Create audiobook from text with cloned voice of author or character
  • Transcribe meetings and dictate text locally without sending audio to cloud

// QUICK START

brew tap debpalash/tap
brew trust --cask debpalash/tap/voicestudio
brew install --cask debpalash/tap/voicestudio

Commands are taken from the repository README — check the current version on GitHub before running.

#ai#audiobook#cuda#dubbing#elevenlabs-alternative#huggingface#local-first#mlx#omnivoice-studio#speech-to-text#text-to-speech#transcription
Open on GitHub →

New repositories every 30 minutes

REDDYX AI scans GitHub 24/7 and ships the best AI/ML/Web3 projects to Telegram.

Join on Telegram
← Full catalog·Full index

// SIMILAR REPOSITORIES

NVIDIA NEMO SPEECH — FRAMEWORK FOR SPEECH AI AND MULTIMODAL LLMS★ 18764OFFLINE SPEECH PROCESSING ON ONNXRUNTIME★ 16007LOCAL VOICE DICTATION FOR ALL OS★ 6802DOCKER WRAPPER KOKORO-82M TTS WITH OPENAI API★ 5706VIETNAMESE TTS WITH ON-DEVICE INSTANT VOICE CLONING★ 3432SMALL ENGLISH TTS MODEL 4.5M PARAMETERS★ 673

← FULL CATALOG

debpalash/VoiceStudio — Local AI Voice Studio With Cloning…