debpalash/VoiceStudio

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

What it solves

VoiceStudio is a local-first audio workstation that eliminates the need for cloud-based subscriptions and API keys for high-quality voice cloning, dubbing, and transcription. It provides a unified interface for multiple AI audio engines, allowing users to generate speech and transcribe audio while keeping data on their own hardware.

How it works

The project uses a Tauri-based desktop shell with a React frontend and a FastAPI backend. It acts as a registry for various Text-to-Speech (TTS) and Automatic Speech Recognition (ASR) engines (such as OmniVoice, WhisperX, and CosyVoice), routing requests to the local GPU (CUDA, MPS, ROCm) or CPU. It also provides an OpenAI-compatible API and an MCP server for integration with other tools and agents.

Who it’s for

It is designed for creators, developers, and privacy-conscious users who need professional audio tools for voice cloning, video dubbing, audiobook production, and system-wide dictation without relying on hosted services.

Highlights

  • Local-first workflow: Core audio generation and transcription stay on the machine by default.
  • Extensive engine support: Includes 16 TTS and 11 ASR engines covering over 600 languages.
  • Advanced audio features: Zero-shot voice cloning, voice design based on attributes, and video dubbing with speaker preservation.
  • Productivity tools: System-wide dictation widget with optional local-LLM cleanup and vocal isolation using Demucs.
  • Developer-friendly: Offers an OpenAI-compatible audio API and support for MCP clients.

Related

  • Project
    jamiepine/voicebox

    An open-source, local-first AI voice studio for voice cloning, speech generation, and system-wide dictation, featuring an MCP server for AI agent integration.

  • Project
    sybil-solutions/local-studio

    Local Studio is an open‑source macOS/desktop app that lets you run, manage, and chat with self‑hosted LLM back‑ends (vLLM, SGLang, llama.cpp, MLX). It combines a Bun + Hono controller (model lifecycle, OpenAI‑compatible proxy, GPU metrics) with a Next.js/Electron UI and an integrated Pi coding‑agent. The UI works locally or can point at a remote controller, and a companion mobile app (KittyLitter) can pair to reuse the same sessions. The repo provides full dev‑setup scripts, production build instructions, and a CI‑driven release pipeline.

  • Project
    abus-aikorea/voice-pro

    An AI-powered multimedia tool that integrates speech recognition, translation, and voice cloning for automated dubbing and multilingual content creation.

  • Project
    collabora/WhisperLive

    WhisperLive is an open‑source, near‑real‑time transcription server built around OpenAI’s Whisper model. It supports multiple inference back‑ends (faster‑whisper, NVIDIA TensorRT, Intel OpenVINO, AMD ROCm), offers word‑level timestamps, hot‑word boosting, speaker diarization and optional translation, and provides both simple command‑line clients and a Python streaming API. Docker images are provided for GPU and CPU deployments, and browser/iOS extensions let you transcribe audio directly from a web page or mobile device.

  • Project
    Blaizzy/mlx-audio

    MLX‑Audio is a Python library (with CLI, web UI, and Swift package) that runs a large collection of modern speech and music models on Apple Silicon via the MLX framework. It supports TTS, STT, speech‑to‑speech, voice cloning, VAD/diarisation, and music generation, offering quantised 3‑ to 8‑bit variants for low‑memory inference. Install with `pip install mlx-audio`, generate audio via `mlx_audio.tts.generate …` or the Python `load_model(...).generate` API, and optionally serve an OpenAI‑compatible REST API.