Fish Speech is a lightning-fast text-to-speech engine that reproduces a speaker's timbre, accent and emotion from a 15-second sample, then reads any text in that voice with human-like fluency. Built on proven So-VITS-SVC and Bert-VITS2 architectures, the platform hosts dozens of community voices and lets users upload private models, adjust speed, pitch and tone, and export studio-grade WAV or MP3 files for videos, games or IVR systems without expensive re-recording sessions.
Your personal, proactive Google AI assistant that simplifies work, school and everyday life right on your phone
✓Free
Fastest gateway to Gemini multimodal models with 2 M token context, caching and search grounding
✓FreeGenerate realistic, physics-aware videos up to one minute from text, images or existing footage
