> For the complete documentation index, see [llms.txt](https://teamhelp.sipgate.co.uk/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://teamhelp.sipgate.co.uk/use-sipgate/sipgate-app/can-i-retrieve-my-ai-generated-channel-data-via-api-interface.md).

# Can I retrieve my AI-generated channel data via API interface?

Note: This feature is only available to customers with a contract signed before August 25, 2025.

#### What requirements must be met?

With the sipgate app, you can use AI functions to create transcripts, summaries, tasks, and smart answers for each of your conversations. These are then automatically saved in the sipgate app. As an admin, you can also use a webhook to transfer the saved information from the shared channels to external databases or your CRM system for further analysis or processing. We explain how this works in this article.

Important: All admins share the same configuration. If several users of an account have the admin role, existing settings of one admin may be overwritten by the changes made by another admin.

First, you need a URL to which the data is automatically sent as soon as all AI-generated content is available after a phone call.

Important: Only calls from shared channels are taken into account here. Private phone calls are excluded from data transfer.

#### Where do I enter the configuration data?

As an admin open the sipgate desktop app, go to Labs → AI Assistant Webhook. Enter the desired target URL there and save it. After each call from a channel, all AI-generated content will be transferred to this URL as a bundle via the webhook.

Important: The content is sent automatically after each channel call – however, it may take a moment, as the transfer only takes place once all AI-generated content is available.

#### What does it look like?

The data is generally provided in json format. However, you can set in the sipgate app whether it should be output in vCon format. "vCon" stands for Virtualized Conversations and is a special format for storing and sharing conversation data such as chat logs, transcripts, and recordings. You can find more information about this format [here](https://ietf-wg-vcon.github.io/draft-ietf-vcon-vcon-container/draft-ietf-vcon-vcon-container.html).

#### This is the JSON payload without vCON:

```json
{
  "callHeadline": "Customer asked about product availability and pricing",
  "call": {
    "id": "call_12345",
    "caller": "+491751234567",
    "callee": "+498912345678",
    "startTime": 1718202000000,
    "endTime": 1718202300000,
    "duration": 300,
    "direction": "inbound"
  },
  "channel": {
    "id": "channel_98765",
    "name": "Sales Hotline"
  },
  "transcriptions": [
    {
      "speaker": "caller",
      "startTime": 0,
      "endTime": 5000,
      "text": "Hi, I wanted to ask if the new product is available."
    },
    {
      "speaker": "callee",
      "startTime": 5001,
      "endTime": 10000,
      "text": "Yes, it is available and currently on a promotional offer."
    },
    {
      "speaker": "caller",
      "startTime": 10001,
      "endTime": 15000,
      "text": "Great! How much does it cost with the discount?"
    },
    {
      "speaker": "callee",
      "startTime": 15001,
      "endTime": 20000,
      "text": "The discounted price is 49.99 Euros including VAT."
    }
  ],
  "summary": "The caller inquired about the availability and pricing of a new product. The agent confirmed availability and provided the discounted price.",
  "note": {
    "content": "Customer seemed interested in the promotional offer and may convert soon."
  },
  "actionItems": [
    {
      "id": "action_1",
      "text": "Follow up with the customer in 2 days to offer further assistance."
    }
  ],
  "smallTalkItems": [
    {
      "id": "smalltalk_1",
      "topic": "Weather",
      "description": "Caller mentioned the sunny weather at the beginning.",
      "pinned": false,
      "dismissed": false
    }
  ],
  "smartAnswers": [
    {
      "id": "smartanswer_1",
      "question": "Is the new product available?",
      "answer": "Yes, it is currently available and on promotion."
    },
    {
      "id": "smartanswer_2",
      "question": "What is the price?",
      "answer": "The promotional price is 49.99 Euros including VAT."
    }
  ]
}
```

If you have any further questions about AI Assistant Webhooks, please write to us at: <labs@sipgate.de>


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://teamhelp.sipgate.co.uk/use-sipgate/sipgate-app/can-i-retrieve-my-ai-generated-channel-data-via-api-interface.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.