Ontelio Censori API Documentation

© 2025 Ontelio, Inc.
Document Version: v1.07.03
Last Updated: 06/21/2025
Contact: support@ontelio.com

This document is provided for informational purposes only. Ontelio makes no warranties, express or implied, in this document.

---

Overview

Ontelio offers APIs for:

• Transcription
• Speaker Diarization
• Call Analysis

Key Terminology

1. Transcription – Extracting spoken content from audio or video into JSON text.
2. Speaker Diarization – Segmenting transcription by speaker identity.
3. Call Analysis – Evaluating sentiment and emotion at the utterance level, integrating prosody (tone, pitch, pace, and pauses) to understand emotional state and intent.

---

API Integration Summary

To use Ontelio:

• Transcription/Diarization:
  Endpoint: {BASE_URL}/transcribe

• Analytics (Sentiment, Emotion, Prosody, etc.):
  Endpoint: {BASE_URL}/analytics

API Call Order

1. First: Call the /transcribe endpoint with the audio file.
2. Then: Use the JSON response from transcription as input for any of the following analytics calls:
   • Sentiment
   • Emotion
   • Prosody
     These can be executed in any order or in parallel.

Note: All Ontelio API results are returned via webhooks, including a jobId for tracking.