Features
Text-to-Speech in 140+ languages
750+ Default voices and 500+ Pro voices
Expressive V1.0 VoiceModel (prompt-based emotional storytelling)
Studio Grade Stitching for long-form audio continuity
Multi-Speaker Mode for conversational dialogue
VoxFX™ with over 100 voice effects
Pronunciation Editor and subtitle generation (SRT, TXT)
Speech-to-Text in 90+ languages
VoxStudio™: Music Sense, Voice Enhancer, Voice Isolator
File upload (PDF, DOC, TXT) for batch conversion
RESTful API with geolocation routing (~75ms latency)
Team Workspace with role-based access
Multi-track Projects with background music
900+ AI voices in 142 languages and accents
Instant voice cloning from 1-minute audio sample
Professional voice cloning powered by GPT-4o
AI voice editor for multi-voice dialogue generation
Real-time streaming text-to-speech
SSML support for fine-grained speech control
30+ emotional expressions per voice
WordPress plugin for blog-to-audio conversion
Zapier integration for workflow automation
Pronunciation dictionary for custom words
Punctuation-based pause control
Deepgram integration for enhanced synthesis
1M+ free characters on signup
Unlimited downloads on paid plans