Case Studies

Built with AssemblyAI - Wordcab

In our Built with AssemblyAI series, we showcase developer projects, innovative companies, and impressive products created using the AssemblyAI Speech-to-Text transcription API and/or our Audio Intelligence API. Our latest post features Wordcab.

Built with AssemblyAI - Wordcab

Table of contents

In our Built with AssemblyAI series, we showcase developer projects, innovative companies, and impressive products created using the AssemblyAI Speech-to-Text transcription API and/or our Audio Intelligence APIs such as Sentiment Analysis, Auto Chapters, Entity Detection, and more.

Describe what you’ve built with AssemblyAI.

Wordcab is an API that converts conversations (calls, podcasts, events) into human-sounding summaries with the power of Deep Learning. The key to generating great summaries is having clean transcripts with accurate Speaker Diarization.

Users can feed text transcripts or audio files directly into our API. If they feed a raw audio file, we use AssemblyAI to transcribe it before feeding it into our summarizer.

What was the inspiration for your product?

The world increasingly relies on remote meetings, creating a deluge of recorded audio, video, and text data. Professionals don't have time to overview 30-minute transcripts or audio recordings - whether this is a manager overviewing their hunters' performance or a QA team checking on customer reps' support calls.

With Wordcab's summary API, transcript read times (and listening times) are reduced by an average of 90%, allowing professionals to quickly sift through dozens of calls. We're currently the most advanced conversation summary API on the market, operating on a B2B2C/B model, partnering with Voice Intelligence platforms to integrate advanced summary features into their platforms.

What AssemblyAI features do you use?

For audio files, we transcribe multi-speaker conversations. We need precise diarization, since summaries reference speakers by their label. We also need accurate transcription, as this is directly reflected in the quality of the summary.

Why did you choose to build with AssemblyAI?

Out of all the providers we tested, AssemblyAI was the most accurate, especially on the diarization side.

We're excited for AssemblyAI's continuous improvements to its transcription accuracy and diarizer.

Do you have a demo of your product?

This YouTube tutorial walks you through the basics of our summarization API: