The Most Accurate and Inclusive Speech-to-Text Technology
Our flexible speech-to-text API easily integrates into your services, solutions and applications – giving you the most accurate transcription, powered by machine learning.
Get Started
Our speech-to-text API is quick and easy to use. We give you all the tools you need to deploy, operate, and manage our technology.
- Python
- cURL
- CLI
1import requests
2
3url = "https://asr.api.speechmatics.com/v2/jobs"
4payload = {'config': '{"type": "transcription", "transcription_config": {"language": "en"}}'}
5files = [('data_file', ('file', open('/path/to/file', 'rb'), 'application/octet-stream'))]
6headers = {'Authorization': 'Bearer insert-api-key-here'}
7
8response = requests.request("POST", url, headers=headers, data=payload, files=files)
9
10print(response.text)What Makes Speechmatics Unique
Our unique speech-to-text API is used by businesses across the world. It enables them to accurately understand and transcribe human-level speech into text, regardless of demographic, age, gender, dialect or location. Here are just some of the things that set us apart.
Our Footprint is Global
Speechmatics covers the majority of the global population's native languages with unsurpassed accuracy. When you combine this precision with our accent and dialect robustness, you know you’re getting the best speech-to-text out there.
Innovative Features
By using the latest machine learning approaches, we're constantly finding new ways to better understand human speech. Automatic Language Identification and Speaker Labels are just some of the many features we offer.
Flexible Deployment
The fastest way to get started is to use our cloud service. If you want security-sensitive data to remain within your own environment, no problem. We offer on-premises deployment. Since we have common APIs, you can also pick a hybrid deployment option. Whatever you choose, rest assured that we provide a secure, robust service.
“The introduction of Speechmatics’ speech-to-text solution to drive subtitling processes means (Red Bee) are once again at the cutting edge of broadcasting technology.”
Graham Wilkinson
Presentation and Content Manager, Channel 4
Technical Articles
Whisper Deep-Dive and the Future of AI
Key takeaways from Whisper and what it means for future AI research.
How to Successfully Achieve Multinode Training in PyTorch
Turn a single node training setup into a robust, platform agnostic, multinodal one.
The Future of Word Error Rate
What the alternatives to WER are, as well as arguing a case for more useful approaches.
Featured Case Studies
How Prosodica unlocked valuable voice data and delivered improved caller experiences
How 3Play Media have improved its captioning service for accessible videos
How Red Bee Media is taking the most accurate ASR on the market to provide same-language subtitling for pre-recorded content
Ready to Understand Every Voice?
Sign up to our free speech-to-text SaaS Portal and we’ll guide you through the integration of our API. We pride ourselves on offering the best support for your business needs. If you have any questions, just ask.