Get Started
Build voice-powered applications with the Gradium API. Our TTS and STT models deliver natural-sounding output with best-in-class accuracy, low latency, semantic VAD for turn-taking, and adaptive delay controls for realtime agents.Installation
Install the Python SDK and make your first API call.
Text-to-Speech
Convert text to natural-sounding speech with streaming support.
Speech-to-Text
Transcribe audio in real time with semantic VAD and flush.
API Reference
Explore the full REST and WebSocket API reference.
Explore
Voice Library
Browse available voices or create custom voice clones.
Voice Settings
Control speed, temperature, and voice similarity.
Turn-Taking
Use semantic VAD and adaptive delay for conversational agents.