GlobalSpeech is an information capturing platform which enables healthcare IT system providers to deliver seamlessly integrated digital dictation and speech recognition capabilities to hospitals, clinics, transcription companies and group practices.

Because we understand how much your work and patient safety depend on accurate information, we always strive to find ways to facilitate every type of reporting use case. GlobalSpeech incorporates various modules, all of which relfect our sole motivation and goal: providing you with professional speech recognition technology that speeds up your medical reporting while offering high flexibility to customise it to your individual needs.

Increased productivity
Using Globalspeech enables end users to create reports more efifciently by offering the possibility to dictate directly into templates, using Auto-texts, i-felds and commands. Globalspeech increases the productivity of medical transcription, which results in reduced backlogs and faster turnaround time. Accurate information is available on time, making it possible for doctors to increase quality of care.

Intelligent Speech Interpretation
Globalspeech developed intelligent Speech interpretation (iSi) technology and allows the understanding of natural language, thus reducing the correction effort for both the transcriptionists and the physicians who look after the reporting process themselves.
It leaves out the ‘um’s and ‘eh’s, ignores dialogue that is not part of the dictation, implements corrections that are dictated as part of the text, fills the information into forms, and even rephrases sentences.
GlobalSpeech formats and organises text, for example adding section headings, numbering lists and inserting standard blocks of content.
In fact, Globalspeech emulates the capabilities of a good medical transcriptionist in order to generate usable reports with a minimum of human intervention.

“The recognized text is the final report, because the Globalspeech system is so accurate. More than half of the reports need no correction at all, it’s got it word-perfect. I’ll press authorize and the report is gone – totally finished. I never have to revisit it again.”
(Melanie Hiorns – Consultant Radiologist and Chair of Radiology Great Ormond Street Hospital for Children NHS Trust (GOSH) London)


Deployed at more than 140 sites in 7 countries.
Eliminate turnaround time:
Speech recognition is a fast and convenient method to create medical documentation and input information into electronic medical records. Reports can be validated by the author instantly at the point of dictation.

Increase transcription productivity:
Reading and editing text drafts delivered by backend speech recognition is significantly faster than transcribing recorded dictations. Productivity gains in transcription departments range up to 70%.

Industrial grade
GlobalSpeech captures dictated information and automatically generates formatted and structured medical information — whether for a small practice, a large hospital, or a group of hospitalsFlexible workflows
GlobalSpeech allows the user to choose their preferred and most efficient worklflow to capture medical information — switch between frontend and backend recognition when required or use both.

You can change the way of working anytime. Decide whether you want to have the recognition done in the background (backend), want to see the recognised text immediately and directly edit it yourself (frontend) or, after dictating, send the dictation to a transcriptionist (deferred frontend).

Medical formatting
GlobalSpeech transcribes dosages, measurements, etc. into a standardized format; GlobalSpeech ensures full compliance to medical standards.


GlobalSpeech is seamlessly integrated into information systems (IS) or reporting solutions, enabling the enduser to efficiently capture information within their familiar working environment.

Across the world
GlobalSpeech supports the largest language portfolio in the industry with 25 recognition languages and provides 150 specialised recognition vocabularies (ConTexts).

Speech recognition implementations are described as very profitable IT projects, allowing an increase in productivity by speeding up turnaround time and allowing the reallocation of the budget money saved.

Immediate and continuous adaptation
GlobalSpeech automatically and continuously adapts to the way you dictate based on your final reports.

Optional Initial Training
Training of the voice user profile is not required. We recommend initial training for non-native speakers.

ROI less than 2 years!