Quick Start
Text-to-Speech Quickstart
Generate speech from text in minutes
Voice Agents Quickstart
Create and deploy your first voice agent
Text-to-Speech
Generate ultra-realistic speech from text with our advanced TTS models. Clone custom voices from audio samples in seconds, control pronunciation and emotion, and stream audio in real-time for seamless conversational experiences. Key Features:- Instant voice cloning - Create custom voices from audio samples in seconds
- Real-time streaming - Low-latency audio generation for conversational AI
- Multiple formats - Support for MP3, WAV, and PCM audio formats
- Fine-grained control - Adjust temperature and top-p model parameters
- Production-ready - Built for scale with high availability and reliability
Voice Agents
Build intelligent voice agents that can handle phone calls, answer questions, and interact with users naturally. Deploy agents with phone numbers, configure behavior with prompts and knowledge bases, and monitor performance with comprehensive analytics. Key Features:- Phone number integration - Purchase and assign phone numbers directly through the API
- RAG-powered knowledge bases - Connect agents to your data for accurate, context-aware responses
- Real-time conversation handling - Natural interruptions, turn-taking, and conversation flow
- Comprehensive analytics - Track call history, performance metrics, and agent behavior
- Customizable behavior - Fine-tune prompts, greetings, and agent personality