Features
Real-time speech-to-speech translation over WebSocket
Voice preservation (tone, emotion, timing)
Dubbing for video, podcasts, and audio (10 languages)
Desktop app for macOS with Zoom/Meet/Teams integration
Pinch Rooms for browser-based multilingual meetings
50+ languages with auto-detection
Relay-1 model for speech-to-speech translation (30+ languages)
Pay-as-you-go pricing, no subscriptions
$5 free credits on signup
SDKs for Node, Python, and browser
MCP connector for Claude integration
Support for overlapping speech (no turn-taking required)
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
