> ## Documentation Index > Fetch the complete documentation index at: https://docs.cognigy.com/llms.txt > Use this file to discover all available pages before exploring further. # Create scenario from transcript > Create a scenario draft by analyzing a conversation transcript. The system uses LLM to extract user intent, conversation goals, and user characteristics from the transcript, then generates an appropriate persona package. The endpoint supports: - Fetching transcript via sessionId from analytics service (RPC call) - Direct transcript content via transcriptContent - Optional flow context for enhanced persona generation - Content safety validation (warnings only, non-blocking) Priority: If both sessionId and transcriptContent are provided, sessionId takes precedence. Returns a complete persona package and metadata about the analysis. ## OpenAPI ````yaml https://api-trial.cognigy.ai/testing/openapi/openapi-viewer.json post /personas/from-transcript openapi: 3.0.0 info: title: SIMULATOR OPENAPI REST-ful-API Reference version: 2025.20.0 description: > ### Introduction This is the [OpenAPI 3.0](https://swagger.io/specification/) documentation of the [REST](https://en.wikipedia.org/wiki/Representational_state_transfer)-ful SIMULATOR OPENAPI API. ### Cross-Origin Resource Sharing This API features Cross-Origin Resource Sharing (CORS) implemented in compliance with [W3C spec](https://www.w3.org/TR/cors/), which allows cross-domain communication from the browser. All responses have a wildcard same-origin header which makes the API completely accessible. ### Authentication SIMULATOR OPENAPI offers following forms of authentication: - Bearer Token (JWT) - API Key ### Error Handling This API uses HTTP status codes equal or above 400 to indicate errors. Error details are generated in compliance with [RFC 7807 - "Problem Details for HTTP APIs"](https://tools.ietf.org/html/rfc7807). Every error response contains a traceId, which should be provided to the SIMULATOR OPENAPI Technical Support when reporting an error. contact: name: Cognigy Technical Support url: https://www.cognigy.com email: support@cognigy.com license: name: Cognigy Proprietary License servers: - url: https://api-trial.cognigy.ai/testing description: Cognigy Service Testing API security: - bearerAuth: [] - apiKeyAuth: [] tags: - name: Simulations description: >- Simulation management operations - Create, read, update, and delete simulations externalDocs: description: SIMULATOR OPENAPI Documentation url: https://docs.cognigy.com/docs/service-testing/ paths: /personas/from-transcript: post: tags: - Personas summary: Create scenario from transcript description: > Create a scenario draft by analyzing a conversation transcript. The system uses LLM to extract user intent, conversation goals, and user characteristics from the transcript, then generates an appropriate persona package. The endpoint supports: - Fetching transcript via sessionId from analytics service (RPC call) - Direct transcript content via transcriptContent - Optional flow context for enhanced persona generation - Content safety validation (warnings only, non-blocking) Priority: If both sessionId and transcriptContent are provided, sessionId takes precedence. Returns a complete persona package and metadata about the analysis. operationId: createScenarioFromTranscript parameters: - name: projectId in: query required: false schema: type: string description: Project identifier (alternative to projectReference in body) requestBody: required: true content: application/json: schema: type: object properties: projectReference: type: string description: >- Project reference for context identification (alternative to projectId query parameter) sessionId: type: string description: >- Session identifier to retrieve transcript from analytics service. If provided, takes precedence over transcriptContent. transcriptContent: type: object description: >- Direct transcript content. Optional if sessionId is provided. properties: messages: type: array description: Array of conversation messages items: type: object properties: source: type: string enum: - user - bot - agent - suggestion description: >- Message source type: 'user' (customer), 'bot' (AI agent), 'agent' (live human agent), 'suggestion' (system suggestion) content: type: string description: Message content timestamp: type: string format: date-time description: Message timestamp required: - source - content - timestamp required: - messages flowId: type: string description: >- Optional: Flow ID to associate with and extract agent context for enhanced generation numberOfSuccessCriteria: type: integer description: >- Optional: Number of success criteria to generate (default: 5, min: 1, max: 10) minimum: 1 maximum: 10 default: 5 analysisOptions: type: object description: Optional analysis configuration properties: maxTurns: type: integer description: 'Limit transcript to first N turns (default: no limit)' minimum: 1 focusOnUserGoals: type: boolean description: 'Focus analysis on extracting user goals (default: true)' examples: withSessionId: summary: Request with sessionId (fetches from analytics service) value: projectReference: 683ef2a378a878cc6550f78b sessionId: session-8f9046b1-6f80-474c-9ce7-24866dbd7cf3 flowId: 683ef3d978a878cc6550fb9d numberOfSuccessCriteria: 5 withTranscriptContent: summary: Request with direct transcript content value: projectReference: 683ef2a378a878cc6550f78b transcriptContent: messages: - source: user content: Hi, I need help unlocking my account timestamp: '2025-10-22T10:00:00.000Z' - source: bot content: I can help you with that. Can you provide your email? timestamp: '2025-10-22T10:00:05.000Z' flowId: 683ef3d978a878cc6550fb9d numberOfSuccessCriteria: 5 responses: '200': description: Scenario created successfully from transcript content: application/json: schema: type: object properties: success: type: boolean description: Whether the generation was successful personaPackage: type: object description: Generated persona package properties: simulationName: type: string description: Generated scenario name personaName: type: string description: Generated persona name personaDescription: type: string description: >- Generated persona description capturing user characteristics mission: type: string description: Generated mission based on user goals successCriteria: type: array description: Generated success criteria items: type: object properties: name: type: string description: Success criterion name text: type: string description: Success criterion description required: - name - text required: - simulationName - personaName - personaDescription - mission - successCriteria metadata: type: object description: Analysis metadata properties: transcriptSummary: type: string description: Brief summary of the analyzed transcript analysisTimestamp: type: string format: date-time description: When the analysis was performed warnings: type: array description: Content safety warnings (if any) items: type: string turnCount: type: integer description: Number of turns in the transcript extractedIntents: type: array description: User intents/goals extracted from transcript items: type: string messages: type: array description: Original transcript messages items: type: object properties: source: type: string enum: - user - bot - agent - suggestion description: Message source content: type: string description: Message content timestamp: type: string format: date-time description: Message timestamp required: - source - content - timestamp required: - transcriptSummary - analysisTimestamp - messages required: - success - personaPackage - metadata example: success: true personaPackage: simulationName: Account Unlock Request personaName: Frustrated Traveler personaDescription: >- A business traveler who is tech-savvy but stressed due to being locked out of their account before an important flight. Communicates directly and expects quick resolutions. mission: >- Unlock the account quickly to access booking information for an upcoming flight successCriteria: - name: Account Unlocked text: User successfully regains access to their account - name: Booking Confirmed text: User can view and confirm their flight booking details - name: Security Verified text: Account security is verified and strengthened metadata: transcriptSummary: >- 8-turn conversation (4 user, 4 bot): "Hi, I need help unlocking my account. I have a flight in 2 hours..." analysisTimestamp: '2024-10-22T10:00:43.000Z' warnings: [] turnCount: 8 extractedIntents: - Unlock account - Access flight booking - Verify travel details messages: - source: user content: >- Hi, I need help unlocking my account. I have a flight in 2 hours and I cannot access my booking. timestamp: '2024-10-22T10:00:00.000Z' - source: bot content: >- Hello! I can help you unlock your account. Can you please provide me with your email address? timestamp: '2024-10-22T10:00:05.000Z' - source: user content: My email is traveler@example.com timestamp: '2024-10-22T10:00:15.000Z' - source: bot content: >- Thank you. I have found your account. For security purposes, can you verify your date of birth? timestamp: '2024-10-22T10:00:20.000Z' - source: user content: January 15, 1985 timestamp: '2024-10-22T10:00:30.000Z' - source: bot content: >- Perfect. Your account has been unlocked. You should now be able to access your booking. timestamp: '2024-10-22T10:00:35.000Z' - source: user content: Thank you! Can you confirm my flight details? timestamp: '2024-10-22T10:00:45.000Z' - source: bot content: >- Your flight is scheduled for today at 12:00 PM, Flight AB123 to New York. timestamp: '2024-10-22T10:00:50.000Z' '400': description: Bad Request - Invalid input parameters content: application/json: schema: type: object properties: error: type: string description: Validation error message required: - error examples: missingTranscript: value: error: One of sessionId or transcriptContent is required invalidMessages: value: error: transcriptContent.messages must be an array emptyTranscript: value: error: Transcript must contain at least one message invalidSource: value: error: >- Message source must be one of: user, bot, agent, suggestion transcriptTooShort: value: error: Transcript must contain at least 2 messages, got 1 invalidSessionId: value: error: sessionId must be a non-empty string sessionNotFound: value: error: >- No valid transcript messages found for session session-xyz. The conversation may be empty or contain only system messages. '401': description: Unauthorized - Invalid or missing authentication content: application/json: schema: type: object properties: error: type: string description: Unauthorized error message code: type: string description: Unauthorized error code traceId: type: string description: Trace ID for debugging required: - error '403': description: Forbidden - Insufficient permissions content: application/json: schema: type: object properties: error: type: string description: Forbidden error message code: type: string description: Forbidden error code traceId: type: string description: Trace ID for debugging required: - error '500': description: Internal Server Error - Server error content: application/json: schema: type: object properties: error: type: string description: Error message code: type: string description: Error code traceId: type: string description: Trace ID for debugging required: - error security: - bearerAuth: [] - apiKeyAuth: [] components: securitySchemes: bearerAuth: type: http scheme: bearer bearerFormat: JWT description: JWT Bearer Token for authentication apiKeyAuth: type: apiKey in: header name: X-API-Key description: API Key for authentication ````