Benedetta Cevoli

Senior Machine Learning Engineer

YouTube’s automated captioning service is notoriously unreliable and represents the dire need for innovation within the speech-to-text industry. Find out what we’re doing about it.

YouTube’s automated captioning service is notoriously unreliable and represents the dire need for innovation within the speech-to-text industry. Click to see what we’re doing about it.

YouTube’s Captions Represent the Dire Need for Speech-to-Text Innovation

YouTube’s Captions Represent the Direct Need for Speech-to-Text Innovation

Technical

Speechmatics Logo New

Editorial team

Explore sample efficiency in the speech recognition industry. Discover cutting-edge techniques and benefits across industries. Unlock the potential of ASR.

Cambridge Science and Tech Wide Open Day

Sample Efficiency and What it Could Mean for Industry

Adam Walford

Senior Site Reliability Engineer

Speechmatics has recently switched from CPUs to GPUs to run most batch transcription models. Better hardware = increased accuracy. Find out more!

GPU Transcription Models

Autoscaling with GPU Transcription models

Headshot of Data Engineer, Steve Kingsley

Steve Kingsley

Data Engineer

Speechmatics’ ASR system (Ursa) surpasses competitors such as Amazon, Microsoft, and Google in real-time accuracy even when operating at a latency setting as low as 2s, while competitors are set to their highest latency, most accurate configurations. Furthermore, Ursa maintains near batch level performance across different latency requirements.

Best in class ASR system

Best-in-class real-time ASR system

Lawrence Atkins

Machine Learning Engineer

David MacLeod

Machine Learning Architect

Quantizing neural networks offers the promise of improved performance and efficiency, but achieving those gains on GPUs can be hard! This blog explains why, and shares solutions that we use in practice.

Fast and Accurate GPU Quantization for Transformers

Caroline Dockes

Speechmatics are proud to announce our real-time voice translation service. Combining our existing best-in-class speech-to-text allows us to offer highly accurate real-time translation, in our single speech API. Try it out today!

Real-Time Translation

Introducing Real-Time Translation: Breaking Down Language Barriers

Bethan Thomas author pic

Our latest Ursa release was able to achieve incredible accuracy partly through scaling self-supervised learning. In this blog we demonstrate the power of self-supervised learning and challenge the assumption that scaling labeled data is the key to greater accuracy. We show that with 300x less the amount of labeled data we still beat the nearest vendor by 12% relative.

Self-Supervised Learning

Boosting sample efficiency through Self-Supervised Learning

Ana Olssen

Speechmatics' newest model, Ursa, performs better than ever on specialized topics like medicine and finance.

Join Ana Olssen as she explains how we can understand every voice in specialized domains by relying on self supervised learning combined with powerful language models.

Domain Generalization image

Ursa: Scaling up as a Solution to Domain Generalization

In a world of increasingly costly machine learning model deployments, ensuring accurate GPU operation timing is key to resource optimization. In this blog post, we explore best practices to achieve this in PyTorch.

PyTorch timing operations

How to Accurately Time CUDA Kernels in Pytorch

By combining the output of an automatic speech recognition (ASR) system with a large language model such as GPT-4 and ChatGPT, we can do many downstream tasks in a zero-shot way by including the transcript and task in the prompt.

GPT-4 - What You Need To Know

Accuracy Matters When Using GPT-4 and ChatGPT for Downstream Tasks

Ten questions to Stuart Wood, Director of Product, on the economics of speech at scale, how close local accuracy now gets to cloud, and who could benefit from Speechmatics On-Device.

On-device speech-to-text, in 10 questions

Sign In

Get started

Contact sales

Speech-to-Text API

Capabilities

Text-to-Speech API

Agent STT

Speech-to-text

Medical and healthcare-Navigation icon

Medical & Healthcare

Legal icon

Legal Transcription

technical-blog-icon

AI Voice Agents

media-and-captioning-icon

Media Distribution & Captioning

meeting-platforms

Note-Taking & Meeting Assistants

contact center icon

Contact Center Solutions

By Use Case

blog-icon

News & Articles

events-icon

Partnerships

contact-us-icon

Contact Us

careers-icon

Careers

about-speechmatics-icon

Find Out More About Speechmatics

case-studies-icon

Case Studies

Resources

Technical information

documentation-icon

service-status-icon

Service Status

Inclusivity

Community

Technical blog

announcement-icon

GitHub Academy

market-exposure-icon

Startup Program

Developers

Enterprise

Security

Pricing

Advanced speech recognition API with high accuracy across [<langcount>] languages.

Speechmatics Speech-to-Text

Get started with our speech recognition API

Free

Speechmatics

Advanced features for professional use ($0.24 per hour)

Custom solutions for large-scale deployments

We are Speechmatics. Global experts in deep learning and voice technology. Accurate speech-to-text for analysis and accessibility.

Speechmatics Social Sharing

Global experts in deep learning and voice technology. Accurate speech-to-text for analysis and accessibility.

Stay up-to-date with the very latest product news, company news and artificial intelligence (AI) research. Bookmark our technology blog today!

Blog & Latest Speech Recognition News| Speechmatics

Company

Product

Use Cases