Create from a Description
Generate a voice agent from a natural language description
Lemu uses an LLM to generate the initial workflow definition from your description. The result is a fully editable agent — use Update to refine it after creation.
Provide a conversation_outline describing what the agent should do, along with call_type (inbound or outbound). Optional fields let you steer the result further: company_name, capture_fields, input_variables, guardrails, tone, agent_gender, and language/voice defaults (tts_language, stt_language, voice).
This is the fastest way to get a working agent, especially for common use cases like appointment booking, lead qualification, or customer support.
Note: no
POST /api/v1/workflow/create/from-promptoperation was found in the OpenAPI spec.