AIToolScan

Voicebox Overview

Voicebox is an open-source AI voice studio that runs entirely on your local machine — a free, local alternative to ElevenLabs and WisprFlow for voice cloning, dictation, and agent voice output.

• Voice Cloning: Clones any voice from as little as a 3-second audio sample with natural intonation and emotion.
• 7 TTS Engines: Bundles Qwen3-TTS, Chatterbox, Chatterbox Turbo, LuxTTS, Qwen CustomVoice, TADA, and Kokoro out of the box.
• Dictate Anywhere: Hold a global shortcut to dictate into any app on macOS or Windows, powered by Whisper STT (99 languages).
• MCP Integration: Give Claude Code, Cursor, Cline and any MCP-aware agent a cloned voice with one tool call (voicebox.speak).
• Local REST API: Every engine becomes a localhost endpoint — no API keys, no rate limits, no per-character fees.
• Cross-Platform: Native apps for macOS (Apple Silicon \/ Intel), Windows, and Linux with Metal, CUDA, ROCm, Intel Arc, or DirectML acceleration.
• Open Source: MIT licensed and 100% local — your audio never leaves your machine.