Skip to main content
POST
/
agents
/
{agent_id}
/
transcripts
/
{session_id}
/
summarize
Summarize Transcript
curl --request POST \
  --url https://api.example.com/agents/{agent_id}/transcripts/{session_id}/summarize \
  --header 'Authorization: Bearer <token>'
{
  "action_items": [
    "Send confirmation email"
  ],
  "call_type": "support",
  "key_moments": [
    "Agent offered a 10% credit which resolved the issue"
  ],
  "outcome": "resolved",
  "sentiment": {
    "agent_performance": "Agent handled the situation professionally",
    "customer_satisfaction": "Customer was satisfied with the resolution",
    "overall": "positive",
    "score": 0.7
  },
  "summary": "Customer called about a billing issue. Agent resolved it by applying a credit.",
  "topics": [
    "billing",
    "account credit"
  ]
}

Documentation Index

Fetch the complete documentation index at: https://docs.mrassistant.ai/llms.txt

Use this file to discover all available pages before exploring further.

Authorizations

Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Path Parameters

agent_id
string<uuid>
required
session_id
string<uuid>
required

Query Parameters

include_sentiment
boolean
default:true

Include sentiment analysis

include_topics
boolean
default:true

Extract main topics

include_action_items
boolean
default:true

Extract action items

max_summary_length
integer
default:300

Maximum summary length in words

Required range: 50 <= x <= 1000

Response

Successful Response

AI-generated transcript summary and analysis.

summary
string
required

Concise summary of the conversation

sentiment
SentimentAnalysis · object

Sentiment analysis

topics
string[]

Main topics discussed

action_items
string[]

Follow-up actions identified

key_moments
string[]

Key moments in the conversation

outcome
string | null

Call outcome: resolved, escalated, etc.

call_type
string | null

Type of call: support, sales, inquiry, etc.