Voicebox for Mac

Voicebox is an open-source multimedia application designed specifically for macOS, enabling users to create and synthesize voice profiles locally. Utilizing the advanced Qwen3-TTS model, it generates high-quality voice audio without relying on cloud services or subscriptions. Users can produce realistic audio outputs by crafting voice profiles from short samples, effectively capturing the original tone and accent. Additionally, the integration of Whisper enhances functionality by converting audio to text, streamlining the dialogue editing process for users.

Beyond voice synthesis, Voicebox offers a local voice server through its REST API, facilitating automation for narration and notifications. The application also supports system audio capture, allowing users to record sounds from various sources. Furthermore, it includes a story generation feature, enabling users to create narrated content based on specific scenarios. While the voice cloning process is user-friendly, opportunities exist for enhancing voice customization options and fine-tuning audio samples for improved realism.