POST
/
startE2ESession
curl --request POST \
  --url https://api.simli.ai/startE2ESession \
  --header 'Content-Type: application/json' \
  --data '{
  "apiKey": "<string>",
  "faceId": "tmp9i8bbq7c",
  "ttsProvider": "Cartesia",
  "ttsAPIKey": "<string>",
  "ttsModel": "sonic-turbo-2025-03-07",
  "voiceId": "a167e0f3-df7e-4d52-a9c3-f949145efdab",
  "systemPrompt": "<string>",
  "firstMessage": "<string>",
  "maxSessionLength": 3600,
  "maxIdleTime": 300,
  "language": "en",
  "customLLMConfig": {
    "model": "gpt-4o-mini",
    "baseURL": "<string>",
    "llmAPIKey": "<string>"
  },
  "createTranscript": false
}'
"<any>"

The Simli Auto API offers a quick and easy way to make an end-to-end real-time interaction. Simli Auto now supports custom LLMs, but if you need even more composability, check out the Simli Compose API Reference instead.

This endpoint allows you to start a new end-to-end session.

for changing the interaction languages, you can look at the support list on Deepgram’s website

Body

application/json

Response

200
application/json
Successful Response

The response is of type any.