Features
Dialect-aware automatic speech recognition (ASR)
Natural language understanding and reasoning
Text-to-speech with regional accents and tone control
Customizable guardrails and fallback flows
Workflow engine for system integration
No-code Agent Studio for conversation design
Simulation environment for testing agents
Call transcription, scoring, and analytics
Tool calling and native function execution
<500ms streaming turn-taking latency
75+ concurrent call support
100+ voices across markets
Telephony integration (inbound/outbound)
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
