Stay organized with collections
Save and categorize content based on your preferences.
Conversational Insights uses conversation data that you upload to a Cloud Storage bucket. You can provide your conversation data to the API as either audio or text files.
Optional. Custom categories for the conversation data.
Category
Conversation data category. If you provide categories with your conversation data, they will be used to identify topics in your conversations. If you don't provide categories, the system will automatically categorize conversations based on the content.
Field
Type
Description
display_name
string
Required. A display name for the category.
Entry
Data for a single conversation message.
Field
Type
Description
text
string
Required. The text for this conversation message.
user_id
integer
Required. A number that identifies the conversation participant. Each participant should have a single user_id, used repeatedly if they participate in multiple conversations.
role
string
Required. The conversation participant role. One of: "AGENT", "AUTOMATED_AGENT", "CUSTOMER", "END_USER".
start_timestamp_usec
integer
Required. The timestamp for the start of this conversation turn in microseconds of UTC time since Unix epoch.
Example
The following shows an example of a conversation data file.
{
"conversation_info":{
"categories":[
{
"display_name":"Category 1"
}
]
},
"entries": [
{
"start_timestamp_usec": 1000000,
"text": "Hello, I'm calling in regards to ...",
"role": "CUSTOMER",
"user_id": 1
},
{
"start_timestamp_usec": 5000000,
"text": "Yes, I can answer your question ...",
"role": "AGENT",
"user_id": 2
}
]
}
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Hard to understand","hardToUnderstand","thumb-down"],["Incorrect information or sample code","incorrectInformationOrSampleCode","thumb-down"],["Missing the information/samples I need","missingTheInformationSamplesINeed","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-09-04 UTC."],[],[],null,["# Conversation data format\n\nConversational Insights uses conversation data that you upload to a Cloud Storage bucket. You can provide your conversation data to the API as either [audio](/contact-center/insights/docs/ingest-conversations-api#audio) or [text](/contact-center/insights/docs/ingest-conversations-api#transcripts) files.\n\nConversation transcript data\n----------------------------\n\nYour text files include the following details.\n\n### Conversation\n\nThe top-level object for conversation data.\n\n### ConversationInfo\n\nThe metadata for a conversation.\n\n### Category\n\nConversation data category. If you provide categories with your conversation data, they will be used to identify topics in your conversations. If you don't provide categories, the system will automatically categorize conversations based on the content.\n\n### Entry\n\nData for a single conversation message.\n\n### Example\n\nThe following shows an example of a conversation data file. \n\n```\n{\n \"conversation_info\":{\n \"categories\":[\n {\n \"display_name\":\"Category 1\"\n }\n ]\n },\n \"entries\": [\n {\n \"start_timestamp_usec\": 1000000,\n \"text\": \"Hello, I'm calling in regards to ...\",\n \"role\": \"CUSTOMER\",\n \"user_id\": 1\n },\n {\n \"start_timestamp_usec\": 5000000,\n \"text\": \"Yes, I can answer your question ...\",\n \"role\": \"AGENT\",\n \"user_id\": 2\n }\n ]\n}\n```"]]