Blog

Improved WER - Speech-to-Text Accuracy vs. Google, AWS (May 2020 Update)

Product Updates
AssemblyAI Speech-to-Text API Improved Accuracy WER (Word Error Rate)

You may have noticed a fresh new look this month in the AssemblyAI dashboard, along with improvements to transcription accuracy, and 100% uptime this past month! Below are more details on everything we've been working on this month:

New AssemblyAI Dashboard

We launched updates to improve the overall API experience for our customers - everything from sign-up, to onboarding, and tracking usage more granularly on a daily and monthly basis. Some of the main highlights include:

  • API Analytics - filterable insights about your transcription usage over time
  • Refreshed Design - simplified UI, with added details for things like billing and user permissions
  • Added Support - directly connect with you account manager

New Accuracy Improvement Across All Models

With our most recent update, we are consistently out-benchmarking all other API's in accuracy on our asynchronous English model. Below are our average accuracy %'s (using Word Error Rate or WER) based on benchmark reports run this month versus Google Cloud's video model, AWS Transcribe, and Microsoft Azure:

WER Results - May.png

Curious to compare our accuracy against your current speech-to-text provider? Send 5 of your files to us and we'll come back with a full benchmark report more here.

tw-top-5-ways-ci-is-transforming-sales-and-marketing.png

Upcoming Webinar: Conversation Intelligence with CallRail

5 ways sales and marketing professionals are using AI to clear the path to purchase

Date: July 21st at 11am PST (8am EST)

CallRail’s Senior Product Manager, Christina Bourne, and Demand Gen Marketing Manager, Rachel Ward, will be joined by AssemblyAI’s CEO, Dylan Fox. Together, they’ll explain how conversation intelligence can help your organization achieve great results.

What you'll learn:

  • Visualize voice data to reveal surprising customer insights
  • Take the guesswork out of qualifying leads
  • Learn which products and techniques close deals
  • Use keyword spotting to find out which channels work best
  • Improve your sales team’s conversion rate and conversation quality

Save your seat

100% Uptime

Another month of 100% uptime across all our models, subscribe to our status page to stay up-to-date!

Subscribe to our blog!

Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.

You may also like

Checkout some of our recent research and product updates

Getting started with HttpClientFactory in C# and .NET 5
Developer
Getting started with HttpClientFactory in C# and .NET 5

HttpClientFactory has been around the .NET ecosystem for a few years now. In this post we will look at 3 basic implementations of HttpClientFactory; basic, named, and typed.

Feature Announcement: Content Safety Detection
Product Updates
Feature Announcement: Content Safety Detection is now GA!

Automatically transcribe audio and video files, and surface sensitive content, such "Hate Speech" or "NSFW" content, found within the audio.

Changelog: New Speaker Diarization model released
Changelog
Changelog: New Speaker Diarization model released

We have released a new Diarization model. Speaker diarization is the process of partitioning an input audio stream into homogeneous segments according to the speaker identity.

ADVANCED TRANSCRIPTON FEATURES

Unlock your media with our advanced features like PII Redaction,
Keyword Boosts, Automatic Transcript Highlights, and more