What does Speechmatics do?

Speechmatics provides speech technology and Voice AI for enterprises, offering accurate Speech-to-Text, Text-to-Speech, and Voice Agent solutions. Our models understand every voice and accent across 55+ languages, helping businesses unlock the full potential of voice data.

How accurate is Speechmatics Speech-to-Text?

Speechmatics delivers best-in-market accuracy, achieving up to 99% word accuracy and 96% medical keyword recall in industry benchmarks. Our models handle multiple accents, noisy environments, and multi speakers with ease.

What makes Speechmatics Text-to-Speech different?

Our low-latency Text-to-Speech (TTS) delivers lifelike, human-sounding voices with sub-150ms latency that is ideal for real-time conversations. Developers can stream natural speech in multiple voices and deploy it in the cloud, hybrid, or on-prem for privacy and control.

Can I build real-time voice agents with Speechmatics?

Our voice AI enables developers to build real-time voice agents that listen, understand, and respond naturally. Plug in fast with a flexible API and native integrations to power your AI voice agents.

Which industries use Speechmatics?

Speechmatics is trusted by organizations in media, healthcare, contact center, medical, finance, legal, education, and accessibility. Our technology powers transcription, translation, call analytics, and voice AI applications worldwide.

Can Peppa Pig really educate future generations?

When you think of subtitles – or captions – what springs to mind? That they are useful when you can’t turn the sound up on your phone in a public space?

That they provide accessibility and understanding to videos and tv programmes for the deaf or hard of hearing community. Me too… until recently when I read an article in The Times by Greg Hurst. The article is titled Subtitles on children’s TV boost reading skills.

The article states that

“International studies showed that primary school children who watched television with subtitles were more likely to reach expected standards of reading — and more likely to handle advanced texts — than those who did not.”

In a generation where children are exposed to hours of television programmes or on-demand content on tablets, it’s a wonder why this has never been thought of before.

It’s no secret that automatic speech recognition (ASR) has improved.

Leaps and bounds over the past few years and is increasingly being used across all platforms to subtitle content, improving accessibility for the deaf community or situationally disadvantaged people. I’ve worked closely with subtitling technology and of course, ASR for over two years and I admit, I didn’t see this one coming. The application of subtitles automatically switched on for children’s programmes as a learning tool has never come up. So why not?

Well, the technology is there to do it, but it is ultimately at the discretion of the broadcasters to switch on subtitles by default. And it doesn’t come without its challenges. Whilst ASR is a cost-effective solution to providing subtitles, there are still challenges when it comes to background noise in the programme affecting the quality of audio going into the ASR engine. It is also important to ensure punctuation is used correctly in the subtitles to provide children with the right education. These challenges must be taken into consideration with regards to improving child literacy.

We work with educational platforms such as Instructure and Udemy that provide educational learning tools to people globally. Specifically, we work with Instructure to subtitle educational videos to ensure all content on their video platform – Arc – is accessible. Ensuring the videos are subtitled encourages self-learning of reading and listening at the same time but also expands the audience to include those that are deaf, hard of hearing, disabled or situationally disadvantaged. The introduction of “always on” subtitles for children’s programmes can only expand and enhance the opportunities that are already available on the market today.

Either way, in a world where we are always striving for more knowledge and faster learning, I’m excited to see another use case coming to the fold for ASR and subtitling that improves accessibility and to witness our innovative technology advancements continuing to have a positive impact on society. It seems that Peppa Pig really could educate future generations in more ways than we thought.

Georgina Robertson, Senior Communications Manager, Speechmatics