Voice

Fish Audio

Open-weight and API-based TTS platform with rapid zero-shot voice cloning.

Overview

Fish Audio delivers fast, expressive text-to-speech with strong multilingual support and a zero-shot cloning capability that requires only a few seconds of reference audio. It bridges open-source research and production-ready APIs.

Best for

rapid voice cloning
multilingual storytelling
indie game NPC dialogue

Trade-offs

vs ElevenLabs

Fish Audio offers faster inference and competitive cloning with lower latency; ElevenLabs provides broader voice library and more fine-grained emotional controls.

What XeroHack pre-wires

When you pick Fish Audio in the interview, the engine emits these files into your scaffold:

3-second clone upload
language auto-detect
streaming JSON output

Coupon

No active coupon for this tool right now. Sign in to be notified when one is available.