Transcript Scenario Generation

Upload and parse a transcript file

Upload a single transcript file for parsing and content extraction. This is the second step in the three-step workflow.

The file is streamed directly to Redis via the streamUpload middleware, then:

Read back from Redis
Parsed based on file type (PDF, CSV, DOCX)
Analyzed for speaker labels (Agent/Customer)
Stored as structured data in Redis (keyed by requestId)

Multiple files can be uploaded by calling this endpoint multiple times with the same requestId. The generate endpoint retrieves all files for the request by requestId.

POST

transcript-upload

Upload and parse a transcript file

curl --request POST \
  --url https://api-trial.cognigy.ai/testing/v1/transcript-upload \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: multipart/form-data' \
  --form 'requestId=<string>' \
  --form transcript='@example-file' \
  --form 'projectId=<string>'

{
  "success": true,
  "fileId": "f1e2d3c4-b5a6-7890-fedc-ba0987654321",
  "fileName": "customer_support_call.pdf",
  "fileSize": 245678,
  "fileType": "pdf",
  "textLength": 2450,
  "processedAt": "2026-02-08T14:30:00.000Z"
}

Authorizations

Authorization

string

header

required

JWT Bearer Token for authentication

Query Parameters

projectId

string

Project identifier

Body

multipart/form-data

requestId

string

required

Request ID from the create-request step

transcript

file

required

Transcript file (PDF, CSV, or DOCX)

projectId

string

Project identifier

Response

File uploaded and parsed successfully

success

boolean

required

fileId

string

required

Unique file identifier

fileName

string

required

Original file name

fileSize

integer

required

File size in bytes

fileType

enum<string>

required

Detected file type

Available options:

pdf,

csv,

docx

textLength

integer

required

Length of extracted text content

processedAt

string<date-time>

required

Last modified on July 2, 2026

Generate scenarios from uploaded transcriptsGenerate 3 distinct simulation scenarios from previously uploaded and parsed transcript files. This is the third and final step in the three-step workflow. The endpoint: 1. Retrieves all uploaded files from Redis for the given requestId 2. Combines all transcript content 3. Validates minimum word count 4. Calls the LLM via RPC to generate 3 scenarios 5. Cleans up Redis data after successful generation Each generated scenario includes a simulationName, personaName, personaDescription, mission, and success criteria - ready to be used for creating simulations.

Upload and parse a transcript file

curl --request POST \
  --url https://api-trial.cognigy.ai/testing/v1/transcript-upload \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: multipart/form-data' \
  --form 'requestId=<string>' \
  --form transcript='@example-file' \
  --form 'projectId=<string>'

{
  "success": true,
  "fileId": "f1e2d3c4-b5a6-7890-fedc-ba0987654321",
  "fileName": "customer_support_call.pdf",
  "fileSize": 245678,
  "fileType": "pdf",
  "textLength": 2450,
  "processedAt": "2026-02-08T14:30:00.000Z"
}