Voice Agent API: real-time conversations
Build voice agents over WebSocket: VAD, voice function calling, events, and SIP phone integration.
16 lessons About 1 h Developer
What you'll learn
- Open a real-time WebSocket session authenticated with ephemeral tokens and configured through session.update
- Process PCM and G.711 audio streams while managing automatic speech detection
- Handle the client-to-server and server-to-client event cycle of a conversation
- Trigger voice function calling and built-in tools during a live exchange
- Connect a voice agent to telephony through SIP and LiveKit, and convert audio in Python
Course details
- Who it's for
- Developers, engineers, and integrators who want to use Grok through the API in their applications.
- Prerequisites
- Able to read Python or JavaScript and JSON, plus basic command-line skills. An API key from the xAI console to try the examples.
- Length
- 1 h · 16 lessons
- Format
- 100% online and self-paced, available 24/7 from any browser. Your progress is saved, so you can pick up where you left off at any time. Estimated time: 1 h.
- Assessment
- Self-assessment with the key takeaways at the end of each lesson, and hands-on practice applying the examples to your own use cases. A final quiz of 5 questions with answers, at the end of the last lesson, lets you check what you've learned.
- Accessibility
- This course is designed to be accessible to people with disabilities: text content compatible with screen readers, keyboard navigation, and compliant color contrast. For any accommodation request, email [email protected].
- Price
- Free
- Recognition
- Certificate of completion issued by Corsen AI, verifiable online.
- Syllabus
- Download the syllabus (PDF)