### Answer Based on the available documentation, I can answer part of your questions, but the sources don't contain complete information about sending text input to an active voice call. ## Getting the callId from RetellWebClient When you call the [Create Web Call]() endpoint, the response includes the

call_id

. [(1) ]() The response contains: - `call_id`: Unique id of the call, used to identify the call in the LLM websocket and authenticate in the audio websocket - `access_token`: Used to start the call with

RetellWebClient.startCall()

You should store the

call_id

from the create web call response before starting the call:

javascript
await retellWebClient.startCall({
  accessToken: createCallResponse.access_token,
}) ;

[(2) ]() ## Sending Text Input Mid-Conversation The available sources do not document a specific API method or endpoint for sending text messages to an active web call. The RetellWebClient SDK documentation shows methods for

startCall()

and

stopCall()

, and events for receiving updates, but does not show a method for sending text input. ## Conversation Flow with Text Input The sources don't explicitly document whether voice agent workflows (question nodes, extract variable nodes) can accept text input mid-conversation and continue the flow normally. --- I'd recommend checking these potentially useful sources for more details: - [Connect to web call]() - [LLM WebSocket]() - [Create Web Call]() You may also want to reach out via [Contact Sales]() or check the [GitHub]() for more information on this specific use case. Would you like me to try providing a general answer based on my knowledge instead?

​ To learn more, see the sources I considered: [[1] Create Web Call](https://docs.retellai.com/api-references/create-web-call) [[2] Connect to web call](https://docs.retellai.com/deploy/web-call) ​

Feel free to tag @AI Evy with additional questions. I also appreciate feedback, it helps me improve.