Features
Open-source voice agent framework
Modular design for AI stack flexibility
Supports multiple STT and TTS providers
Real-time voice interaction orchestration
Enterprise-grade API for phone calls
Python SDK for integration
Node.js SDK for integration
React SDK for web app integration
Abstractions for building voice LLM agents
Self-hosted or managed deployment
Text-to-speech in 55+ languages
Upload PDF, DOCX, TXT files
Multiple AI voices (male/female)
Emotional tones: angry, calm, cheerful, sorrowful, etc.
Adjust speaking rate and pitch
Export as MP3, WAV, or SRT
Multi-speaker audio creation
Video dubbing with voice cloning (Pro/Team)
Batch conversion for multiple files
Text highlight during playback
SSML support for pronunciation
Cloud-based (web, iOS, Android)
History of converted audio files
