ODMS Cloud v2 Adds Powerful AI Speech Recognition Capabilities

Voiced by Amazon Polly

OM System has just launched version 2 of its ODMS Cloud platform, and one of the headline features in this release is built-in speech recognition. Designed for professionals who rely on secure, fast, accurate dictation, the new speech-to-text functionality streamlines the transcription process by converting dictations into editable text automatically — no transcription required. ODMS Cloud is an Australian hosted digital dictation and transcription workflow solution from OM System, formerly Olympus Audio.

Whether you’re in the legal, medical, or business field, this update offers real advantages for busy professionals who need to produce documents quickly, efficiently and accurately.


Automatic Speech Recognition with Microsoft Azure AI

At the heart of this new feature is Microsoft’s Azure AI platform — a cloud-based speech engine used by enterprise organisations around the world. Once enabled, ODMS Cloud v2 can automatically transcribe dictation files as soon as they are uploaded to the cloud including natural language punctuation. No need to dictate your punctuation.

This means recordings made on supported Olympus/OM SYSTEM digital dictaphones or through the ODMS Cloud smartphone mobile dictation app are transcribed in the background. The recognised text is then sent back to the transcriptionist final editing and proofreading. This reduces transcription time dramatically. If you outsource your transcription this results in less hours charged. If you insource your transcription will result in a happy transcriptionist who can recover some valuable time to work on other projects.

For professionals used to outsourcing transcription or spending time manually typing notes, this can dramatically reduce turnaround time.


How It Works

ODMS Cloud’s speech recognition functionality is triggered automatically based on your workflow setup. Once a dictation is securely uploaded, the system:

  1. Integrates with Microsoft Azure’s speech recognition engine to process the digital dictation.

  2. Returns a formatted text transcription.

  3. Presents the result in the ODMS Cloud Transcription Module, where it can be reviewed and corrected as needed.

The transcription editor includes a new Text Correction Window, which highlights each word as it is spoken during playback. This makes it easy to verify the content, make adjustments, and finalise the document in less time.


Key Features

Here are some of the core benefits and features of the ODMS Cloud v2 Speech Recognition module:

  • Automated Transcription: Dictations are converted to text as soon as they are uploaded.

  • Text Correction Window: Synchronised audio-text review interface makes proofing faster and more accurate.

  • Unlimited Use: The speech recognition add-on is licensed on an annual basis and offers unlimited transcription usage.

  • Template Support: Output can be merged with pre-formatted Word templates, saving even more time for admin staff.

  • Workflow Integration: Supports routing rules and team-based document handling, ideal for larger organisations.


Compatibility and System Requirements

To use the speech recognition feature, you’ll need the following:

For more information on ODMS Cloud, digital dictation, transcription and speech recognition solutions contact us as Dictate Australia

Leave a comment

This site uses Akismet to reduce spam. Learn how your comment data is processed.