Voicebox - an open-source local speech synthesis tool, an open-source alternative to ElevenLabs.

What is Voicebox?

Voicebox is an open-source, native speech synthesis tool, a cross-platform desktop application built on Tauri (Rust) and React. The tool offers voice cloning, text-to-speech, audio post-processing, and multi-track narrative editing features. All models and speech data run locally, prioritizing privacy. The project has garnered over 17.4K stars on GitHub and is considered an open-source alternative to ElevenLabs.

Voicebox main functions

• Sound cloning and file managementIt supports creating personalized sound profiles by uploading audio files, recording in real time, or capturing system audio; cloning can be completed in just a few seconds with a clear human voice sample.
• Multi-engine text-to-speechIt has built-in multiple open-source TTS engines such as Qwen3-TTS, LuxTTS, Chatterbox, and TADA, and supports 10-23 languages including English, Chinese, and Arabic to meet different sound quality and speed requirements.
• Professional audio post-processingBased on the Spotify Pedalboard library, it offers 8 audio effects: pitch shift (±12 semitones), reverb, delay, chorus/flaring, compression, gain adjustment, and high-pass/low-pass filters, with support for real-time preview and preset saving.
• Multitrack Narrative EditorThe Stories feature provides a DAW-like multitrack timeline interface, supporting the arrangement, editing, and mixing of different audio files, suitable for dialogue scenarios and podcast production.
• Developer API InterfaceProvides a complete REST API (default port 17493), supporting the generation of voice and management of sound files via HTTP requests, facilitating integration into third-party applications or automated workflows.

How to use Voicebox

• Download and installVisit the official website voicebox.sh Alternatively, you can download the corresponding system version from the GitHub Releases page (macOS is differentiated by Apple Silicon/Intel, Windows provides an MSI installer, and Linux requires a source code build).
• Initialize environmentUpon first launch, the application automatically downloads the required speech model (approximately 2-4GB, such as Qwen3-TTS). All data is stored in the local application directory by default, and no cloud account configuration is required.
• Create a sound fileGo to the Profiles page, select "Create Voice", and capture sound samples by means of Upload (upload file), Record (real-time recording), or System Audio (capture system audio). Enter reference text to complete the file creation.
• Generate speechIn the generation interface, select the created audio file, enter the text to be synthesized, select the target language and TTS engine (such as Qwen3-TTS 1.7B), and click the generate button.
• Post-production and exportIn the Stories editor, you can arrange multiple tracks, apply effects to audio clips (such as robot, radio, echo chamber, and other presets), and then export the finished audio file.

Key information and usage requirements for Voicebox

• System compatibilitySupports macOS 11+ (both Apple Silicon and Intel versions), Windows 10+ (MSI installer), and Linux (must be built from source).
• Hardware configuration requirementsMinimum 8GB of RAM, 16GB or more recommended; at least 5GB of free storage space required; graphics card supporting CUDA/Metal/XPU can significantly speed up inference, and CPU mode is also compatible.
• Data privacy featuresAll speech models, sound files, and generated audio are stored locally and can be used without an internet connection, completely avoiding the risk of privacy leaks from cloud data transmission.
• Open source licenseThe project is open source under the MIT License and can be freely used for personal and commercial purposes. The complete source code and Docker deployment solution are available in the GitHub repository.

Voicebox's core advantages

• Privacy-first local architectureCompared to cloud services like ElevenLabs, Voicebox performs all data processing locally, making it suitable for businesses and individual users who are sensitive to data security.
• Open source ecosystem and cost advantagesCompletely free and open source, with 17.4K+ community stars ensuring continuous updates, avoiding the subscription costs and vendor lock-in of commercial SaaS.
• Professional-level post-production capabilitiesIt features 8 professional audio effects and a multitrack editor based on Pedalboard, providing post-production capabilities rarely seen in similar open-source tools, eliminating the need for secondary processing by exporting to DAW software such as Audacity.
• Flexible switching between multiple enginesIt supports switching between multiple engines, from lightweight 350M models to large 3B parameter models. Users can choose flexibly according to their hardware configuration and sound quality requirements, balancing quality and inference speed.
• Developer-friendly designIt provides a complete REST API and detailed documentation, making it easy to integrate into games, podcast tools, accessibility applications, and other scenarios. It also supports batch generation and management of voice content through code.

Voicebox project address

• Project official websitehttps://voicebox.sh/
• GitHub repositoryhttps://github.com/jamiepine/voicebox

Voicebox Competitor Comparison

Voicebox application scenarios

• Video content dubbingYouTube creators and short video producers can quickly generate high-quality narration for their content, with support for multilingual localization.
• Podcast and Audiobook ProductionUse the multi-track editor to arrange multi-person dialogue scenes and export complete audio works with one click.
• Game development voice actingIndependent game developers can generate dialogue audio for characters, supporting real-time adjustment of mood and tone tags.
• Accessibility tools: To build localized voice assistants for visually impaired users, or to help people with speech impairments communicate by cloning their voices.
• Automated content production: Integrate into the CMS system via API to enable automated voice broadcasting of news articles and weather reports.