Moss Voicev0.1 · beta
Model · not loaded
GitHub
Moss Studio

Type a script. Pick a voice. Hear it in seconds.

A text-to-speech workspace that runs entirely in your browser. Powered by MOSS-TTS-Nano. No servers, no uploads, no audio leaves this tab.

On-device inference Privacy by default ~2s to first audio
01Script
English · neutral
script.txt·en-US
143/ 500·~10s
⌘↵to generate
No audio yet
Generated clips will appear here. They live in this tab only — refreshing clears them.