KariniScribe Agent | Karini AI

KariniScribe Agent processes audio files through a REST API. Follow these steps to integrate and use the service.

Refer to Karini AI documentation  for details

All API requests require authentication using the x-api-token header with your provided API token.

If you have already registered, use the following link to retrieve your token and recipe_id to invoke the agent, Reference: Login to KariniScribe to retrieve your token 

If you need to rotate the api token or any changes to the agent, please contact sales@karini.ai 

• POST requests: 5 requests per minute
• GET requests: 1 requests per minute

Step 1: Prepare Audio File

Upload your audio file (.wav format) to AWS S3 and generate a presigned URL.

Requirements:

• File format: .wav
• Maximum file size: 60 mins recording
• Presigned URL expiration: Minimum 1 hour

Reference: AWS S3 Presigned URL Documentation 

Step 2: Trigger KariniScribe Agent

Initiate Processing

Endpoint: POST /api/webhook/recipe/{recipe_id}

curl -X POST "<https://app.karini.ai/api/webhook/recipe/>{YOUR_RECIPE_ID}" \ -H "Content-Type: application/json" \ -H "x-api-token: {YOUR_API_TOKEN}" \ -d '{ "files": [{ "content_type": "audio/wav", "file_name": "meeting_recording.wav", "file_path": "{S3_PRESIGNED_URL}" }], "input_message": "Make the transcription action-oriented", "metadata": { "session_id": "session_123", "user_id": "user_456" } }'

Response: Returns request_id for tracking processing status.

Step 3: Monitor and Retrieve Results

Get Request Status

Endpoint: GET /api/webhook/request/{request_id}

curl -X GET "<https://app.karini.ai/api/webhook/request/>{REQUEST_ID}" \ -H "accept: application/json" \ -H "x-api-token: {YOUR_API_TOKEN}"

List Recipe Requests

Endpoint: GET /api/webhook/recipe/{recipe_id}

curl -X GET "<https://app.karini.ai/api/webhook/recipe/>{RECIPE_ID}?limit=10" \ -H "accept: application/json" \ -H "x-api-token: {YOUR_API_TOKEN}"