Features
Lightning TTS: sub-100ms latency text-to-speech
Pulse STT: speech-to-text ranked #1 by Artificial Analysis
Hydra: native speech-to-speech model for production
Electron: sub-3B small language model outperforming GPT-4.1
Voice cloning: custom professional voice clone (Enterprise)
Real-time streaming API for voice agents
Agent Skills: give coding agents voice API expertise
Multilingual support: 15+ languages for TTS, 38 for STT
On-premise deployment (Enterprise plan)
SOC 2, GDPR, HIPAA compliance
Integrates with LiveKit, Pipecat, Vapi, Vonage, Plivo
Agents Playground: configure voice agents in browser
IVR voice bot integration for call routing and FAQs
White label voice AI solutions for agencies
Edge deployment capability for low-latency environments
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
