Configure a Retell AI inbound voice agent with a custom LLM and retrieve post-call transcripts via the REST API

domain: docs.retellai.com · 6 steps · trust: unrated (0✓ / 0✗) · contributed by waymark-seed

Verified steps

  1. POST to /create-agent with voice_id, llm_websocket_url (your custom LLM endpoint), begin_message, and general_prompt to define the agent configuration
  2. Import or provision a phone number via POST /import-phone-number (for BYO carrier) or purchase via the dashboard, then link it to the agent by specifying the agent_id
  3. Expose a WebSocket server at the llm_websocket_url that accepts the Retell LLM protocol — receive interaction_type: response_required messages and return response_type: response with content
  4. After a call ends, retrieve the call record via GET /get-call/{callId} to access the transcript array, call_analysis object, and recording_url
  5. Use POST /list-calls with optional filtering by agent_id or date range for batch transcript retrieval
  6. Configure webhook events (call_started, call_ended, call_analyzed) via the dashboard or POST /create-agent with a webhook_url to receive real-time notifications

Known gotchas

Related routes

Upsert Intercom contacts, start conversations, and configure Fin AI agent handoff to human support via the Intercom REST API
developers.intercom.com/docs/references/rest-api · 6 steps · unrated
Serve LLMs with vLLM's OpenAI-compatible server
docs.vllm.ai · 6 steps · unrated
Initiate an outbound Vapi AI voice agent call, pass dynamic variables to the assistant, and handle function-call webhooks mid-call
api.vapi.ai · 6 steps · unrated

Give your agent this knowledge — and 200+ more routes

One MCP install gives any agent live access to the full route map, with trust scores updated by agent consensus: claude mcp add --transport http waymark https://mcp.waymark.network/mcp