This document contains the current API restrictions and usage limits for Conversational Insights. This page will be updated to reflect any changes to these restrictions and usage limits. We reserve the right to change these limits.
You can refer to the quota page for more information on requesting a quota increase.
Google Cloud Console Insights quotas
After submitting your request, Google might contact you for more information and inform you whether your request is approved or denied.
Request quota
The current API usage quota for Insights are as follows (and are subject to change):
Type of Quota | Usage Quota |
---|---|
Total number of requests per minute | 3000 |
CreateConversation requests per minute |
300 |
CreateAnalysis requests per minute |
300 |
ExportInsightsData requests per minute |
60 |
UploadConversation requests per minute |
300 |
The current API resource limits for Insights are as follows (and are subject to change):
Type of Quota | Quota |
---|---|
Conversations per region | 2,000,000 |
Analyses per region | 2,000,000 |
Issue models per region | 10 |
Deployed issue model per region | 5 |
Training operations
Type of Quota | Quota |
---|---|
Concurrent issue model creation operations per region | 1 |
Concurrent faq model creation operations per region | 1 |
Bulk Operations
Type of Quota | Quota |
---|---|
Concurrent bulk analyze conversation operations per region | 1 |
Concurrent bulk ingest creation operations per region | 1 |
Summarization
Conversational Insights uses Agent Assist to generate conversation summaries. When you run summarization for Conversational Insights analyses, you will see an additional line item on your bill for Agent Assist API usage. You may have to request additional Agent Assist quota.
Speech to Text
Conversational Insights uses Speech to Text to generate transcriptions. You may have to request additional quota as specified here.