
Voicebox is a completely open-source, free local AI voice-cloning studio product, integrating three core capabilities: voice cloning, multi-engine TTS generation, and global dictation. It supports 7 TTS engines and 23 languages; all models and voice data run completely offline and are never uploaded. Suitable for content creators, developers, and daily office users — a free alternative to ElevenLabs and WisprFlow.
Software features: fully local offline processing, no internet upload needed, ensuring recording data is secure. Supports real-time recording-to-text, outputting text while recording, extremely efficient. Built-in multilingual recognition model (including Chinese) for different language needs. Export formats support TXT, SRT, etc., convenient for post-editing or subtitle production. Completely free open-source, no usage limits, supports Windows and macOS.
Software screenshots shown.
*Disclaimer: intro only, no revenue commitment; comply with platform rules and law.*