AWS S3 Connector Setup Guide

​

Quick Start (5 Minutes)

1. Enable Quality AI Express in platform settings.
2. Upload test.csv to your S3 folder with sample data.
3. Configure the S3 connector with bucket credentials and paths.
4. Run validation tests to verify connectivity.
5. Set a processing schedule and monitor via logs.

​

Critical Requirements

​

Prerequisites

​

AWS Environment

• S3 bucket created in your preferred region
• IAM user/role with read-only S3 permissions
• Planned bucket folder structure (unified vs. separate paths)
• Test audio/chat files prepared for validation

​

Platform Requirements

• Quality AI Express enabled in settings
• All agents onboarded with correct email addresses
• Service queues configured and ready for mapping
• User has Integrations & Extensions permissions

​

Data Validation

• Audio files in WAV or MP3 format (maximum 50 MB each)
• Mono recordings split into separate agent/customer files
• All timestamps in ISO 8601 format (YYYY-MM-DDTHH:MM:SSZ)
• All recording URLs accessible via HTTPS
• CSV files contain all required metadata fields
• test.csv file created with sample data

​

Supported Recording Types

​

Field Differences by Recording Type

​

Authentication Methods

{
  "Version": "2012-10-17",
  "Statement": [
    {
      "Effect": "Allow",
      "Action": ["s3:GetObject", "s3:ListBucket"],
      "Resource": [
        "arn:aws:s3:::your-bucket-name",
        "arn:aws:s3:::your-bucket-name/*"
      ]
    }
  ]
}

​

Mono Recording Requirements

• conv-123456-agent.wav (agent audio only)
• conv-123456-customer.wav (customer audio only)

• conv-123456-mixed.wav (both speakers mixed)

​

Data Flow Architecture

​

CSV Metadata Formats

​

Stereo Voice Recordings

​

Mono Voice Recordings

​

Voice Transcripts (Pre-transcribed Audio)

​

Chat Scripts (Live Chat Interactions)

​

JSON Transcript Schemas

​

Voice Transcript Format

{
  "recognizedPhrases": [
    {
      "channel": 0,
      "offsetInTicks": 140000000.0,
      "nBest": [
        {
          "lexical": "yes one four three four two six",
          "words": [
            {
              "word": "yes",
              "offsetInTicks": 140000000.0,
              "durationInTicks": 3200000.0,
              "confidence": 0.51653963
            }
          ]
        }
      ]
    }
  ]
}

​

Chat Transcript Format

{
  "1": {
    "type": "AGENT",
    "text": "Good afternoon, how can I help you today?",
    "timestamp": 1749562206000,
    "userId": "john.smith@company.com"
  },
  "2": {
    "type": "USER",
    "text": "I need help with my account balance.",
    "timestamp": 1749562253142,
    "userId": "customer_12345"
  }
}

​

Step-by-Step Configuration

​

Step 1: Prepare S3 Environment

• All audio files are accessible via HTTPS URLs
• CSV files contain required fields with correct headers
• Mono recordings have separate agent/customer files
• test.csv exists in each configured folder
• File sizes are under 50 MB each

​

Step 2: Platform Configuration

1. Navigate to Quality AI > Configure > Connectors.
2. Select + Add Connector > Amazon S3 > Connect.
3. Configure Basic Settings:
   • Name — descriptive connector name
   • AWS Region — your S3 bucket region
   • Auth Type — access keys or IAM role
4. Configure authentication:
   • Access Keys — enter Access Key and Secret Key.
   • IAM Role — enter the IAM Role ARN.
5. Configure folder paths:
   • Unified Path — single path for voice and chat: s3://your-bucket/conversations/
   • Separate Paths — voice and chat paths separately:
     • Voice: s3://your-bucket/voice-interactions/
     • Chat: s3://your-bucket/chat-interactions/

1. Select the Test tab in the connector configuration.
2. Verify all checks pass:

​

Step 3: Queue Mapping and Scheduling

1. Navigate to the Queue tab and map CSV queueId values to Quality AI Express queues. Ensure exact string matches.
2. Navigate to the Schedule tab:
   • Interval — choose frequency (minutes/hours/days)
   • Start Time — set initial run time (UTC timezone)
3. Select Save to activate.

• Queue mappings saved and validated
• Processing schedule configured and active
• First ingestion job appears in the Log tab
• No error messages in processing logs

• Conversations appear in Quality AI Express dashboards
• Analytics data populates for ingested interactions

​

Troubleshooting

​

Authentication Issues

​

Data Processing Issues

​

Performance Expectations