API Documentation
Discover how to launch expressive voice experiences, reliable transcription, and intelligent conversational AI with a consistent REST interface. Choose one of the services below to get started.
Text-to-Speech
Convert text into natural speech using streaming or file-based modes. Learn about the shared payload, chunking preview, and metadata-rich file generation.
View TTS APIs →Speech-to-Text
Upload audio with multipart form data to receive accurate transcripts. Review supported inputs, authentication requirements, and integration snippets.
View STT API →Large Language Models
Generate intelligent chat completions with state-of-the-art language models. Fully compatible with OpenAI SDK for seamless integration. Supports streaming and multi-turn conversations.
View LLM API →Voice Agents
Discover and connect to configured voice agents. Obtain agent listings and LiveKit session details to start interactive voice sessions that combine ASR, NLU, and TTS.
View Voice Agents →Python SDK
Official Python SDK for seamless integration. Features synchronous and asynchronous APIs, streaming support, and comprehensive error handling for production use.
View SDK Docs →