Features
AI text-to-speech with LLM-trained voices
Content-aware voice intonation
Multilingual support in 90+ languages
Voice cloning from recordings or uploads
Voice Design via prompts or presets
AI Podcast: convert documents to audio episodes
AI Recap: generate document summaries
AI Screenshot: analyze captured text/graphs
AI Chat: ask questions about documents
AI Quizzes: create practice tests
Chrome extension for web reading
Mobile apps for iOS and Android
OCR camera scanner for physical books
MP3 export for offline listening
Immersive Reader with highlighted text
AI video dubbing with emotion preservation
Realistic text-to-speech in 30+ languages
Auto-generated subtitles with perfect sync
Voice cloning for branded/custom voices
Multi-speaker support for dialogues
Advanced studio with find-and-replace, transliteration, glossary
Contextual translations using GPT-3.5 or GPT-4
Multiple pronunciation options per word
Royalty-free music library and upload
Link sharing for team collaboration
Bulk actions for projects
Real-time media player with segment-aware skipping
Streaming API with <500ms latency
Credit system: 1 min dub = 4 credits, 1 min sub = 1 credit, 1 min TTS = 2 credits
Batch processing for multiple audio files
