back to top
HomeSoftwareAI ToolsVoicebox – Offline AI Voice Cloning & TTS Studio (Qwen3-TTS, Open Source)

Voicebox – Offline AI Voice Cloning & TTS Studio (Qwen3-TTS, Open Source)

Voicebox – Offline AI Voice Cloning & TTS Studio Qwen3-TTS open source for windows mac and linux
Firethering Team
By Firethering Team
0
Last updated:
- Advertisement -

File Information

FileDetails
NameVoicebox
Versionv0.3.0
Formats .msi • .dmg
Size299MB (exe) • 330MB (dmg)
PlatformsWindows • macOS
LicenseOpen Source (MIT License)
Github RepositoryVoiceBox Github
Official Websitevoicebox
CategoryVoice AI • Speech Synthesis • Audio Tools

Table of contents

Description

Voicebox is a local-first, open-source voice synthesis studio designed for cloning voices, generating realistic speech, and building voice-powered applications directly on your own machine.

It keeps everything local. Your voice samples, models, and generated audio never leave your system, giving you full privacy, ownership & control.

With a DAW-like interface, multi-track editing, and an API-first design, Voicebox is built for creators, developers, and teams who want professional voice tools without usage limits or cloud dependency.

Use Cases

  • Clone voices locally for narration or dialogue
  • Create podcasts, stories, and multi-speaker conversations
  • Build game dialogue and character voice systems
  • Automate voice generation in content pipelines
  • Develop privacy-focused voice assistants
  • Generate speech for accessibility tools
  • Integrate voice synthesis into apps via API
  • Experiment with open-source TTS models safely

Screenshots

Local Voice Cloning & Speech Synthesis Studio
VoiceBox voice synthesis studio powered by Qwen3-TTS.

Features of VoiceBox

FeatureDescription
Local Voice CloningClone voices from short audio samples completely offline
Speech QualityNatural prosody, emotion, and realistic cadence
Studio EditorTimeline-based, multi-track audio composition
Multi-Voice SupportCreate conversations with multiple speakers
Open ModelsPowered by Qwen3-TTS, with more open models planned
API AccessFull REST API for automation and integrations
Native AppLightweight, high-performance desktop app (Tauri)
Apple Silicon BoostMLX backend delivers 4–5× faster inference
Privacy FirstNo cloud, subscriptions, limits, or internet required

System Requirements

Windows

RequirementDetails
Operating SystemWindows 10 or later
Architecture64-bit
RAM8 GB minimum
Disk Space5–10 GB
GPUOptional (CPU supported)

macOS

RequirementDetails
Operating SystemmacOS (Apple Silicon or Intel)
ArchitectureARM64 / x64
RAM8 GB minimum (16 GB recommended)
Disk Space5–10 GB (models + audio)
AccelerationMetal / MLX (Apple Silicon)

How to Install VoiceBox??

Windows (.exe)

  1. Download the Voicebox .msi installer
  2. Run the installer
  3. Follow the setup steps
  4. Launch Voicebox from the Start Menu

macOS (.dmg)

  1. Download the Voicebox .dmg file
  2. Open the DMG
  3. Drag Voicebox.app into the Applications folder
  4. Launch from Applications
    • If macOS shows a security warning, go to
      System Settings → Privacy & Security → Open Anyway

Linux

According to the developer , it is planned to launch the Linux build soon. So as soon as it will be available , we will update the page. But if you want to build it from source, follow the official guide

Recommended For You: Handy: Offline Open-Source Speech-to-Text AI App For Windows, macOS & Linux

How to Use Voicebox (Simple Steps)

Getting started with Voicebox is straightforward just follow the below steps after installation:

  1. Launch the Voicebox app on macOS or Windows
  2. On first launch, select and download a voice model
    • Progress, speed, and status are shown clearly
  3. Once the model is ready, import or record a short voice sample
  4. Voicebox automatically creates a voice profile
  5. Enter your text and generate speech locally
  6. Use the timeline editor to mix voices, trim audio, or build conversations
  7. Export your audio or reuse it later from generation history

Download Voicebox: Local Voice Cloning & Speech Synthesis Studio For Windows & macOS

Download For Windows
Download For macOS (Intel)
Download For macOS (Apple Silicon)

Open Source & Development

Voicebox is developed as a fully open-source project, that means users and developers can:

  • Inspect and audit the source code
  • Contribute features or bug fixes
  • Experiment with new voice models
  • Build custom voice-powered tools

By using Tauri instead of Electron, Voicebox stays lightweight, fast, and memory-efficient while still offering a modern UI.

Conclusion

Voicebox delivers a powerful, privacy-first approach to voice synthesis, combining voice cloning, speech generation & audio editing into one open-source desktop application.

With local execution, native performance, and an API-driven design, it’s well-suited for creators and developers who want professional voice tools without cloud subscriptions.

If you’re exploring voice AI, audio storytelling, or voice-powered applications with control, transparency & performance, Voicebox is a very useful software.

LEAVE A REPLY

Please enter your comment!
Please enter your name here

- Advertisment -
YOU MAY ALSO LIKE

Modly: Open Source Local AI Image-to-3D Model Generator

Firethering Team - 0
You've got a photo and you want a 3D model. Normally that means paying per generation on some cloud service that uploads your image to a server you'll never see. Modly skips all of that. It's a desktop app that converts any photo into a fully usable 3D mesh, right on your own GPU. No files leaving your machine. Drop an image in, the AI handles background removal automatically, reconstructs the geometry, and hands you a model ready to open in Blender, Unity, Unreal, or whatever you're working in.
Lore AI Note manager Desktop app open source

Lore: Local AI Note Manager with Smart Recall & Private Second Memory

Firethering Team - 0
Lore is a lightweight, privacy-first desktop app that lives quietly in your system tray and gives you a pop-up chat interface to capture thoughts the moment they happen. Powered entirely by a local LLM through Ollama and a local vector database through LanceDB, it stores, understands, and retrieves your information without sending a single byte to the cloud. You can store anything like quick notes, decision summaries, URLs, code snippets, bug reproduction steps, todo items and retrieve it all later by simply describing what you need in plain language. Lore classifies your input automatically and uses a RAG pipeline to pull the most relevant context before generating an answer. If you're a developer, a knowledge worker, or someone who just wants a smarter way to remember things, Lore is worth a try.
Recordly Open-Source Screen Recorder & Editor

Recordly: Open-Source Screen Recorder & Editor for Windows, macOS & Linux

Firethering Team - 0
Recordly is an open-source screen recorder and editor built for creating polished, professional-grade screen recordings without juggling multiple tools. Designed for developers, educators, and content creators, it lets you record your screen or a specific window and jump straight into a built-in editor to refine the result before export. What sets Recordly apart is its presentation-first approach. Instead of delivering raw footage, it gives you cursor effects, auto-zooms, webcam overlays, styled backgrounds, and timeline editing all in one place. Whether you're making a product demo, a tutorial, or a social clip, Recordly handles the full workflow from capture to export. The app is fully offline and stores all recordings and project files locally on your device. AI features are not required, and your content never leaves your machine unless you choose to share it.

Don’t miss any Tech Story

Subscribe To Firethering NewsLetter

You Can Unsubscribe Anytime! Read more in our privacy policy