Multilingual Communication Analytics Platform
A unified analytics system for WhatsApp chats and voice calls in mixed Arabic dialects and English. Uncovering actionable insights through cutting-edge AI.
Arabic Dialects & English
WhatsApp & 3CX Voice
Whisper, GPT-4o, RoBERTa
Automated Data Fetching
Seamlessly processing omni-channel interactions through a centralized routing and specialized AI analysis pipeline.
Voice Calls (.wav)
Call Logs & Timestamps
WhatsApp Chat Data
Orchestrator & Type Detection
Extracts sentiment, intents, and bilingual summaries from WhatsApp.
Merges insights across channels, scoring similarity & unified reporting.
Transcribes via Whisper, detects medical specialty inquiries.
Comprehensive analytics leveraging advanced LLMs and fine-tuned models.
OpenAI Whisper Large-v3 with GPT-4o refinement for Arabic dialects & code-switching.
Fine-tuned XLM-RoBERTa 5-class classification (positive, negative, neutral, incomplete, unanswered).
Detects conversation phases (Greeting, Intent, Service, Conflict) and specialty inquiries.
Per-role statistics tracking agent vs. client wait times and first contact detection.
Dual-language context-aware summaries keeping vital details like names, dates, and costs.
Label distribution, message length, and deep conversation pattern visualizations.
Deep dive into agent-level metrics, evaluating adherence to communication flows, efficiency, and overall interaction quality.
Measures completion of the 8-point communication checklist (Greeting, Intent, CTA, etc.)
Aggregated overall quality score based on Politeness, Empathy, Clarity, and Professionalism.
Tracks average agent delay and first response time in seconds across all sessions.
Calculates Customer Satisfaction (CSAT proxy) and Customer Effort Score (1-5).