@yiyirats: When relying on third-party voice services, data privacy and stability are always factors to consider. Voicebox is a locally run AI voice studio; all processing is done locally, data is not uploaded to the cloud, and no account registration is required. The features are quite comprehensive: supports Qwen3-TTS, LuxTTS, Chatterbo…

When relying on third-party voice services, data privacy and stability are always factors to consider. Voicebox is a locally run AI voice studio; all processing is done locally, data is not uploaded to the cloud, and no account registration is required. The feature coverage is quite comprehensive: it supports 7 TTS engines including Qwen3-TTS, LuxTTS, Chatterbox, and Kokoro, covering 23 languages; can clone a voice from just a few seconds of audio with no limit on generation length; includes 8 post-processing effects such as pitch shifting, reverb, and compression; a multi-track timeline editor supports the creation of audiobooks, podcasts, and multi-character voiceovers; and it comes with a global dictation hotkey, allowing you to enter text by voice in any application. On the hardware side, it has native MLX/Metal acceleration for Mac Apple Silicon, and Windows and Linux support CUDA, ROCm, or CPU operation. The project is licensed under the MIT license and has received 33.8k stars on GitHub. Project URL: https://github.com/jamiepine/voicebox…