In this article, you'll learn how to configure your VoiceAgent to effectively capture structured and unstructured data during calls, define output destinations, and ensure seamless integration with your existing business processes.
User Level
Admin
VoiceAgent Data Capture & Output Settings
Cloudtalk VoiceAgents feature not only engages in dynamic conversations but also collects and route key information. VoiceAgents are designed to streamline workflows by automatically extracting relevant data - such as customer details, call intent, or issue summaries - and delivering it to your preferred systems, including CRMs, support tools, and internal databases.
Configuration of the data capture and output behavior of the VoiceAgent can be defined within Data Capture and Output behior setting including:
Call analysis prompt
Call Results Endpoint
How it works?
Once the call concludes, the full transcript is sent to ChatGPT along with your configured Call Analysis Prompt.
The AI processes the prompt and is expected to return a JSON object that includes exactly the fields you have specified.
The resulting JSON output is then delivered to your designated Call Results Endpoint, as configured in your VoiceAgent settings.
Call Analysis prompt
Call Analysis Prompts are executed after the call concludes, leveraging the full conversation transcript to generate structured insights. These prompts use OpenAI (ChatGPT) to analyze the transcript and return results in a predefined JSON format.
This functionality is ideal for extracting key business intelligence - such as customer interest, pain points, CRM tools mentioned, go-live timelines, and demo readiness. The resulting data can be used to automatically populate CRM fields, trigger follow-up workflows, or power reporting dashboards.
Defining What to Extract
Within the Call Analysis prompt, it is necessary to define:
Which fields you want included in the output (e.g.
crm,wants_demo,preferred_date)Field types:
boolean: true or false (e.g., wants_demo: true)string: text (e.g., crm: "HubSpot")number: numerical values (e.g., total_team_size: 5)array: a list (e.g., team_sizes: [2, 3, 4])
Defining extraction Logic Tips
For simple output fields like crm, the AI will typically identify the correct value without additional instructions. However, for more complex fields, include explicit logic in your analysis prompt to guide the AI.
Example: "Total Team Size" is the sum of all team sizes mentioned during the call.
Only information mentioned during the call will be extracted. Add clear logic in your prompt if needed.
Example Call Analysis Prompt
This is a basic example used to extract a single field (name) from the call transcript. It follows all required formatting and response rules for use with CloudTalk's Call Analysis system.
You are a call-analyzing assistant that analyzes sales call transcripts. Your task is to extract key information from the conversation and return it in a specific JSON format.
Only include information that was explicitly mentioned in the conversation.
You must respond with a valid JSON object containing these fields: { "name": string }
Use empty strings for unknown string fields, 0 for unknown numbers, and false for unknown booleans.
Your response must be only the JSON object, without any additional text, markdown formatting, or code blocks.
Call Results Endpoint
The Call Results Endpoint is the destination URL where the structured JSON output - generated from your Call Analysis Prompt - is automatically sent after each call. This endpoint acts as the bridge between your VoiceAgent and your chosen workflows, integrations, or internal systems.
💡 Recommended Tools for Receiving JSON Data:
Webhook.site – great for testing and validating your payloads.
Zapier, Make, or Tray.io – ideal for no-code/low-code automation workflows.
Internal systems – such as custom APIs or backend services that can parse and store the incoming JSON.
Make sure the endpoint you define is accessible and properly configured to receive and handle the structured data in real time.
If you need any further assistance please do not hesitate to reach out to our Support team, we are always happy to help!