Talk

Sends a text message to an active session, allowing the avatar to forward the query to an LLM and speak the generated response.

POST/api/v2/sessions/{sessionId}/talk

Headers

Header	Value
Authorization	Bearer {session_token}
Content-Type	application/json

Body

Parameter	Type	Required	Description
message	string	required	User text (server-side max length enforced)
type	string	optional	Reserved for future use (defaults are fine; no need to set)

Notes

• Sessions are scoped to the appId they were created with.
• You cannot access a sessionId that belongs to a different appId.

Tip: You can use [FIRST_MESSAGE] when you already have the exact text the avatar should say and want to inject that response directly.

Examples

cURL

curl https://ai-streamer.deepbrain.io/api/v2/sessions/${SESSION_ID}/talk \
-H "Content-Type: application/json" \
-H "Authorization: Bearer ${SESSION_TOKEN}" \
-X POST \
-d '{
  "message": "Hello."
}'

Node.js

import axios from "axios";
const sessionId = "${SESSION_ID}";
const sessionToken = "${SESSION_TOKEN}";

axios
  .post(
    `https://ai-streamer.deepbrain.io/api/v2/sessions/${sessionId}/talk`,
    {
      message: "Hello.",
    },
    {
      headers: {
        Authorization: `Bearer ${sessionToken}`,
        "Content-Type": "application/json",
      },
    },
  )
  .then((res) => {
    console.log(res.data);
  })
  .catch((error) => {
    console.error(error);
  });

Python

import requests

session_id = '${SESSION_ID}'
session_token = '${SESSION_TOKEN}'
url = f'https://ai-streamer.deepbrain.io/api/v2/sessions/{session_id}/talk'

headers = {
    'Authorization': f'Bearer {session_token}',
    'Content-Type': 'application/json'
}
body = {
    'message': 'Hello.'
}

response = requests.post(url, headers=headers, json=body)
print(response.json())

Success (code: 1000)

{
  "code": 1000,
  "data": null,
  "message": "Message sent successfully"
}

Next step

Call this API repeatedly to continue the conversation. Use List Sessions or Get Session Detail to manage sessions when needed, and call Stop Session to end the conversation.