Features
Text-to-speech with 200+ AI voices
Adjustable speech rate and pitch
Pause insertion (0.5s to 5s) for logged-in users
Document upload (PDF, TXT) to speech
Custom voice creation / voice cloning
Multi-speaker multilingual TTS (up to 10K chars/audio)
MCP (Model Context Protocol) server integration
AI Skill for agent integration
Ebook-to-audiobook workflow
1000+ lifelike AI voices in 60+ languages with dialects
Voice cloning from 20-second recording
13 emotional tones for expressive narration
Adjustable pitch, speed, pauses, pronunciation
Pronunciation library with custom word notes
AI dubbing for localization in 60+ languages
AI avatars with custom character creation
Stock media library with images, videos, music
Team collaboration with Single Sign-On (SSO)
24/7 phone, email, and chat support
YouTube integration for direct export
API access for developers to integrate TTS
Voice Typing Dictation feature
Voice AI Assistant for instant answers
