May 2022 Summaries

This tutorial demonstrates how to enhance an e-learning platform with features such as speech-to-text, AI-generated topics, and summarization of video lectures using Symbl.ai and api.video. The demo uses Next.js, React, and Typescript, and includes a database to store video IDs with conversation IDs, as well as components to display the intelligence in the UI. The tutorial covers how Symbl asynchronously processes videos, fetches intelligence from the Conversation API, and integrates with the e-learning platform. It also discusses the importance of accessibility and automated content management for e-learning platforms, and provides a high-level architecture diagram. The demo includes features such as speech-to-text transcripts, summary paragraphs, and topic tags, which enhance the user experience and engagement on the online platform.

Developers are invited to participate in a new community video series on Symbl.ai, where they can share their favorite API and why it's their go-to choice. To do so, they need to record a short video clip of themselves explaining their preference, which should be around 5-10 seconds long and filmed vertically with a minimum resolution of 1080 pixels x 1920 pixels. The clips will then be used to create an interactive video montage that will be shared on the Symbl.ai Slack community and social media channels, allowing participants to showcase their voices and start valuable conversations with other developers. By sharing their favorite API, participants can also win some cool developer swag.

A custom classifier is a machine learning model trained to understand and sort unstructured data into predefined categories based on a specific learning objective. It helps humans in characterizing items and then sorting them into categories, making decisions about input data, and transforming raw data before it's fed into the classifier. Custom classifiers are useful in various fields such as object detection, sentiment analysis, audio classification, and more. They use different algorithms and architectures like Perceptron, Naive Bayes, decision tree, logistic regression, K-nearest neighbor, artificial neural networks, support vector machines, and others to achieve their learning objective. By using custom classifiers, engineering teams can build more quickly and efficiently, while also reducing the costs of managing and modifying a production pipeline for classification. The output of a custom classifier is usually an integer representing the predicted class, which is then mapped to the actual class based on a predefined mapping.

This article demonstrates how to integrate Symbl.ai's Conversation Intelligence capabilities with a live video calling app built using the Vonage Video API. The integration enables features such as Live Transcription, Sentiment Analysis, and Speaker Analytics, which provide insights into conversations during video calls. By combining these features, developers can build accessible and engaging video calling applications that cater to diverse user needs. The article provides a step-by-step guide on how to set up the project, integrate Symbl.ai's APIs with Vonage Video API, and run the demo application.