voicebox-voice-synthesis

Skill by ara.so — Daily 2026 Skills collection. Voicebox is a local-first, open-source voice cloning and TTS studio — a self-hosted alternative to ElevenLabs. It runs entirely on your machine (macOS MLX/Metal, Windows/Linux CUDA, CPU fallback), exposes a REST API on localhost:17493 , and ships with 5 TTS engines, 23 languages, post-processing effects, and a multi-track Stories editor. Linux requires building from source: Prerequisites: Bun , Rust , Python 3.11+ , Tauri prerequisites The Python FastAPI backend handles all ML inference. The Tauri Rust shell wraps the frontend and manages the backend process lifecycle. The API is accessible directly at even when using the desktop app. Base URL: Interactive docs: Embed natural language instructions directly in the text: Docker configuration ( docker-compose.yml override): Voicebox auto-chunks at sentence boundaries — just send the full text: Voicebox auto-recovers stale generations on startup. If the issue persists: - Use 5–30 seconds of clean, noise-free speech for voice samples - Multiple samples improve clone quality — upload 3–5 different sentences - For multilingual cloning, use chatterbox engine - Ensure sample audio is 16kHz+ mono WAV for best results - Use luxtts for highest output quality (48kHz) in English