Fish Audio AI Voice Generator

About

The text-to-speech entry point for Fish Audio's S2 engine: paste a script, pick from a library of over 2,000,000 community-uploaded voices across 80+ languages, and export the result as MP3 or WAV. Inline tags such as [whispering] and [excited] control delivery within a script, and a voice can be cloned from about 10 seconds of reference audio. The free tier gives 8,000 credits a month (roughly seven minutes of audio), 500 characters per generation, and three public voice slots, with commercial use and larger credit pools on paid plans.