Features
500+ AI voices across 37 languages
Text-to-speech conversion with WAV/MP3 output
Real-time streaming audio via API endpoint
Timestamp TTS with word/character alignment
Instant voice cloning from short audio samples
Expressive controls for emotion, pacing, format
SDK libraries for 12 programming languages
CLI tool for local workflows
AI-assisted development via Claude Code, MCP, OpenClaw
No-code integrations with Zapier, Make, n8n
Multi-language support including Korean, English, Japanese, Chinese, Spanish
Text-to-speech with emotion tags (angry, sad, excited, etc.)
Voice cloning from 10–15 seconds of audio
2,000,000+ community voice library
Ultra-low latency TTS API
Real-time streaming voice generation
Speech-to-text with multi-speaker and emotion tags
Fish Audio S2.1 Pro: word-level voice control
AI Voice Design: create a custom voice from text prompt
Professional voice cloning (studio-quality verified clones)
Multilingual voice cloning (any voice in multiple languages)
Voice agent end-to-end solution
Podcast transcription tool
Team Plan with collaboration features
Open-source S2 model on GitHub
