Product - Transcription

Great AI transcription: The bedrock of value

Accurate transcription. Valuable on its own. And the foundation for so much more.

We've got it covered

Consistently reliable speech-to-text outputs mean you can focus on delivering value to your customers, not worrying about your transcripts.

Transcripts you can trust

Consistently accurate, in every language

No need to proof read. You focus on downstream activities, we focus on accurate transcription.

Infinitely flexible

Functionality to help fine tune your outputs

A rich feature set that allows you to identify speakers, add your own unique vocabulary, deploy flexibly and more.

Built for the real world

Simplify workflows with our unified API

Integration is simple, with code samples and SDKs to get started. Low-latency (<1s) transcription has never been easier.

Accuracy

Hitting the mark with pinpoint accuracy

Our ASR is best in class

We pride ourselves on our accuracy, outperforming some of the biggest companies in the world across the languages we support.

Our inclusive ASR works regardless of the accent or dialect, even in challenging, noisy environments.

Choose a clip
Play audio
They were known as seers and they were held in fear by women and the elderly.
People (They) have (were) noticed (known) seals (as) seers and they were held in fear by women and the elderly.
Help
The comparison text for ASR providers shows how the recognized output compares to the reference. Words in red indicate the errors with substitutions being in italic (e.g. substitution), deletions (e.g. deletion) being crossed out, and insertions (e.g. insertion) being underlined. Hovering over the substitution error will show the ground truth.

How do we compare?

We compared the relative accuracy of major Speech-text-providers in almost 4 million words, so you don’t have to. Speechmatics outperforms all the major cloud providers as well as Whisper on large publicly available data sets (see the full breakdown here).

Transcription-Dialect comparison

Mitigating AI bias

Speechmatics achieve consistent, reliable and inclusive transcription - regardless of dialect.

We're accurate across all languages, even dialects. Don't believe us? This graph shows a 22% lead over the next best competitor on African-American vernacular English, calculated on the CORAAL dataset. Our innovative Self-supervised Learning (SSL) approach allows us to overcome the lack of well-curated labelled data and brings us a step closer to mitigating AI bias.

The proof is in the pudding. Or budino. Or मिठाई.

Test results are great, but nothing beats a live demo. Below is a live stream of four international radio broadcasts, with live transcription and translation both shown, in real-time.

Breadth and depth in features

Delivering for multilingual, multicultural, and multinational businesses.

Global reach

50 languages, and counting

We support transcription in 50 languages (including local dialects and accents) with automatic language detection, all with unparalleled accuracy.

Formatting

Intuitive, readable transcripts

Correctly formatted numbers, dates, and currencies, as well as language-specific capitalization, means your transcripts will be easy to parse and make sense of.

Features

Custom Dictionary, for the really tricky words

Boost accuracy for proper nouns, acronyms, or industry-specific terms by providing a list of custom words.

Use a unique word in your business? No problem with Speechmatics.

Captions

Real-time and batch transcription

Batch transcripts for the media that can wait. Real-time for the stuff that can’t.

We power captions for live sporting events, so if you need our service in a hurry, no sweat.

Tech

A unified API for simpler workflows

With Speechmatics, all it takes is a single API call.

This includes our growing suite of speech capabilities like summaries and sentiment.

Deployments

SaaS, or on-prem... why not both?

Our API can be deployed on cloud, on-prem or on-device, providing for every security, privacy, and data sovereignty requirement you might have.

Need speed? Prefer accuracy? We'll point you in the right direction

Choose your operating point and get exactly what you need. We offer two proprietary transcription models available to all customers:

Standard

Great for users and generating transcripts where speed is a priority, with accuracy trade-offs as a result.

Enhanced

When unbeatable accuracy is a must-have, our Enhanced model provides best-in-class accuracy across all of our languages.

"We're delighted to work with Speechmatics to drive our live and batch captioning processes – they continue to be ahead of the pack for all our key quality metrics."

Tom WoottonHead of Product Area for Broadcast Services, Red Bee Media
Red Bee new logo

"Speechmatics strives to push boundaries, playing a pivotal role in the development of our workspace. They consistently outperform other vendors for word error rate, speaker segmentation and punctuation."

Maarten VerwaestChief Revenue Officer, Limecraft

“Speech recognition technology is essential for the functionality of our Contact Center applications, so we teamed up with Speechmatics to ensure we deliver the best speech technology on the market."

Mariano TanCEO, Prosodica (part of Vail Systems)

Try It Now. For Free. Without Code.

The BEST way to view Speechmatics' accuracy is to see for yourself, on your media. Head to the portal and get a free account today.

Resources

ASR just got an upgrade. Speech Intelligence is here.

Explore the latest breakthroughs in speech and AI, all built on category leading accuracy.