Solventum™ Fluency Direct™ Voice Recognition

Solventum™ Fluency Direct™ is a voice recognition solution that lets radiologists dictate diagnostic reports directly within the OmegaAI Document Viewer. This article covers installation, configuration, productivity tools, troubleshooting, and a full voice command reference for using Fluency Direct with OmegaAI.

Important: This feature requires a separate purchase. Contact your RamSoft representative or Support to learn more.

Before you begin

Confirm the following before installing or configuring Fluency Direct:

• Supported version: Fluency Direct v14.1.56 or later is required for OmegaAI integration. Versions earlier than v14.1.56 do not support the web connector and must be upgraded before use.
• PowerServer compatibility: Fluency Direct v14.1.56 is compatible with PowerServer 6.0 (with the latest patches applied) and PowerServer 6.7.
• Browser: Google Chrome is recommended. Microsoft Edge and Firefox are also supported.
• Account name: You need your site's account name during installation. RamSoft provides this during onboarding; it is typically a short abbreviation of your site name.
• Region: Know whether your site is in the United States or Canada. This determines which configuration is applied during installation.
• Admin rights: Installation requires administrative rights on the workstation.
• M*Modal license: An M*Modal Fluency Direct license must be assigned to your account before use. Contact your RamSoft sales representative or RamSoft Support to request this.

Install and connect Fluency Direct

This section walks through installing Fluency Direct v14 on a workstation and connecting it to OmegaAI.

Upgrade or migrate from an older version

Fluency Direct v14.1.56 is required for OmegaAI integration. If you are moving from PowerServer to OmegaAI, or you are running an older version of Fluency Direct, follow these steps:

1. Uninstall the existing version of Fluency Direct from the workstation.
2. Download and install v14.1.56. See Download and install Fluency Direct v14.
3. Complete the remaining configuration steps in this article to connect Fluency Direct to OmegaAI.

Note: All user settings — including your profile, dictionary, abbreviations, and commands — are preserved and are available automatically after reinstalling.

Download and install Fluency Direct v14

1. Download the Fluency Direct v14 installer package from the RamSoft Resources page.
2. Extract the ZIP file to a local folder and confirm the following files are present:

RamSoft Fluency Direct Installer.bat custom_settings.US.ini custom_settings.CA.ini fd.client\Fluency.Direct.Client.Install.exe

Caution: Do not proceed if any of these files are missing. A corrupted or incomplete archive results in a broken installation. Re-download the ZIP file if needed.

3. Right-click RamSoft Fluency Direct Installer.bat and select Run as administrator.

   Important: Do not double-click the file to run it — the script requires elevated privileges to complete installation.

   If a User Account Control (UAC) prompt appears, confirm it to allow the script to proceed.

4. When the installer script prompts you, provide the following:

Account name: Enter your site's account name exactly as provided by RamSoft Support. This value is case-sensitive. Region: Enter 1 for United States or 2 for Canada.

Note: Example entry: account DEMO_SITE, region 1 (United States).

5. The script automatically:
   • Backs up any existing custom_settings.ini file to custom_settings.ini.bak.
   • Creates a new custom_settings.ini file from the selected region template, with the account name populated.
   • Launches fd.client\Fluency.Direct.Client.Install.exe.
6. Follow the on-screen prompts in the Fluency Direct client installer to complete installation. In most cases, you can accept the default settings.

Expected result: Fluency Direct is installed on the workstation and ready to be connected to a browser and to OmegaAI.

Enable the Fluency Direct browser extension

The Fluency Direct browser extension extends dictation functionality to web-based applications such as OmegaAI. It is available for Fluency Direct v10.0.400 and later, and it is typically installed automatically by the Fluency Direct client installer.

The following browsers are supported:

• Chrome — Solventum Fluency Direct Web Connector (Chrome Web Store)
• Microsoft Edge — Solventum Fluency Direct Web Connector (Microsoft Edge Add-ons)

Important: Chrome is the only supported browser for Fluency Direct on macOS.

To confirm the extension is active:

1. Open your browser and navigate to the extensions page (for example, chrome://extensions in Chrome or edge://extensions in Edge).

   

2. Locate M*Modal Fluency Direct in the list and confirm its toggle is switched On (blue).

   

Expected result: The M*Modal Fluency Direct extension appears in the browser's extension list with its toggle On.

If this doesn't work: If the extension is not in the list, install it manually using the browser links above, or re-run the Fluency Direct installer (see Download and install Fluency Direct v14).

Launch Fluency Direct and verify the connection

1. Launch Fluency Direct on the workstation, either from the desktop shortcut or by selecting Start > Fluency Direct. The Fluency Direct toolbar appears on screen.

   

2. Left-click the toolbar to open the login prompt, and enter your M*Modal account credentials.

   Note: M*Modal credentials are case-sensitive. If login fails, verify that Caps Lock is off and that your credentials are correct.

   To change the region or account without reinstalling, hold Shift and left-click the toolbar to open the Advanced Settings menu. See Switch accounts or regions without reinstalling.

   

3. Once you are logged in, your name appears on the Control Bar. Open any study from the OmegaAI worklist and launch the Document Viewer. Once the Document Viewer is open, the Control Bar automatically displays the OmegaAI label, confirming that Fluency Direct is targeted to the Document Viewer and ready for dictation.

   

4. Click inside a field in the report and begin dictating. Transcribed text appears at the cursor position in real time.

   

Expected result: Your name appears on the Control Bar after login, the OmegaAI label appears once the Document Viewer is open, and dictated speech is transcribed into the active report field in real time.

If this doesn't work: See Troubleshooting for the OmegaAI label not appearing or the microphone not being detected.

Configure Fluency Direct

Configure the following settings once during initial setup, or again when you change equipment.

Set up your microphone

The Microphone Setup dialog lets you select your input device, assign a record button, and calibrate the microphone to your voice and environment.

1. Left-click the Fluency Direct Control Bar and select Microphone setup.

   

2. Configure the following settings:

   • Microphone — Select the input device to use for recording from the dropdown list.
   • Record button — Assign a microphone button or keyboard key to start and stop recording.
   • Calibration — Click Calibrate... to calibrate the microphone to your voice and surroundings.

3. Optionally, click Advanced to configure additional device button options. See Map device buttons to actions.

For full guidance, see Microphone Setup (Solventum Help Library).

Set your medical specialty

Setting your medical specialty helps Fluency Direct prioritize terminology relevant to your practice, which improves recognition accuracy for specialty-specific language.

1. Left-click the Fluency Direct Control Bar and select Medical specialty.

2. Select your primary specialty from the list (for example, Radiology).

3. Click Save.

   

Note: Radiologists should select Radiology as their primary specialty. This loads radiology-specific vocabulary — anatomical terms, imaging modalities, and common findings — into the active recognition model.

For more information, see Medical Specialty (Solventum Help Library).

Complete profile training

Profile Training introduces you to Fluency Direct features and trains the system to recognize your speech patterns.

1. Left-click the Fluency Direct Control Bar and select Profile training.

2. Click Begin.

3. Dictate each short paragraph presented. Click Skip to move to the next paragraph, or Finish when you are done.

   

For more information, see Profile Training (Solventum Help Library).

Configure general settings

The Settings dialog contains three sections: Formatting, General, and Account settings.

Left-click the Fluency Direct Control Bar and select Settings to open it.

Formatting settings

Formatting settings control how dictated content is transcribed, including:

• Number formatting (numerals vs. words, ordinals, ranges, enumerations)
• Measurements, temperatures, and percentages
• Dates and times
• Contractions
• Clinical notation (cranial nerves, liver segments, spine levels)
• Paragraph and list spacing

Note: Settings marked with a lock icon are administrator-controlled and cannot be changed by the user.

General settings

Setting	Description
Text insertion interval	Controls how frequently words are inserted into the application, using a slider from frequent to less frequent.
Window layout	Remembers the position and size of dialogs and the Control Bar. Select Same across all computers or Per computer. Click Reset saved positions to restore the defaults.

Account settings

Setting	Description
Security question	The question used to verify your identity if you forget your password.
Security question answer	The answer assigned to your security question. Not case-sensitive. Click Change... to update it.
Email address	Used internally to protect your account. Not shared or sold.
Password	Click Change password to update your M*Modal account password.

For more information, see Account Settings (Solventum Help Library).

Use productivity tools

The following tools help you work faster and more efficiently during dictation. Build these up over time and customize them to your workflow.

Use the Speech Box

The Speech Box is an integrated dictation panel that lets you dictate text and transfer it to any application. It is useful when an application does not fully support Fluency Direct navigation, editing, and formatting commands, or when you want to collect dictation in one place while browsing other windows. In this mode, dictation can be targeted to the Speech Box regardless of which window is active on the desktop.

Note: In OmegaAI, dictation is transcribed directly into the Document Viewer. The Speech Box is not required for standard OmegaAI workflows.

Manage your dictionary

The Fluency Direct dictionary lets you add words that are not recognized correctly, such as medical terminology, physician names, facility names, medications, or specialty-specific terms. Words are organized into categories to improve recognition accuracy.

To open the Dictionary, left-click the Fluency Direct Control Bar and select Dictionary.

The dialog has two panels: Categories (left) and the word list for the selected category (right). The following categories are available:

Category	Contents
Person names	Physicians, nurses, and other personnel
Locations	Hospitals, regions, and facility names
Medications	Drug names (for example, temazepam)
Procedures	Procedure names (for example, hysterectomy)
Diagnoses	Acute, chronic, and other diagnostic terms
Other	Words that do not fit elsewhere
Excluded	Words you never want recognized

Add a word

1. Select a category from the left panel.
2. Click + Add to open the Add a word dialog.
3. On the Written form tab, enter the word exactly as it should appear in the transcription. Fluency Direct generates the pronunciation automatically; click Change to edit it if needed.
4. Optionally, click the Spoken form tab to specify how the word sounds rather than how it is spelled. This is useful for acronyms or unusual names — for example, the spoken form of AAA is triple A.
5. Optionally, click the Record pronunciation tab, press your assigned record button, and dictate the word to record a custom pronunciation sample.
6. Click Save.

Tip: Use the Search field at the top right of the Dictionary dialog to check whether a word already exists before adding a duplicate.

For full guidance, see Dictionary (Solventum Help Library).

Create abbreviations

Abbreviations let you dictate a short phrase that automatically expands into longer text. This is useful for standard report phrases, facility names, or frequently used findings.

The Abbreviations dialog lists all existing abbreviations in two columns: Original (the short phrase you dictate) and Replacement (the full text that is inserted).

Add an abbreviation

1. Left-click the Fluency Direct Control Bar and select Abbreviations.

2. Click + Add.

3. In Original, enter the short phrase you will say (for example, UMC).

4. In Replacement, enter the full text to insert (for example, University Medical Center).

5. Click Save.

   

Tip: Use abbreviations for boilerplate report sections, such as normal study templates, standard impression statements, or frequently dictated facility and procedure names.

For more information, see Abbreviations (Solventum Help Library).

Create custom commands

Commands let you create custom voice-triggered actions — such as inserting text, sending keystrokes, or running scripts — and organize them into groups. Commands are more powerful than abbreviations and support multi-step workflows.

To open Commands, left-click the Fluency Direct Control Bar and select Commands. The dialog has two panels:

• Command groups (left) — Lists all available command groups. Your personal commands appear at the top (for example, RAMSOFT DEMO's Commands — Available everywhere). Shared or site-level groups are listed below, marked Limited availability.
• Commands (right) — Lists all commands in the selected group. Click + Add to add a command to the group.

Add a command

1. Select your personal command group from the left panel.

2. Click + Add on the right panel to open the Add a command dialog.

3. Enter a Name for the command. This is the phrase you will say to trigger it (for example, Insert chest normal).

4. On the Steps tab, drag or click a step type to build the command:

   Step type	Description
   Text	Inserts plain text at the cursor position
   Rich text	Inserts formatted text
   Key	Sends a keyboard key or shortcut
   Wait	Adds a pause between steps
   Mouse	Performs a mouse action
   Window	Brings a specific window into focus
   Command	Calls another existing command
   Script	Runs a custom script
   Open	Opens a file or application
   Comment	Adds a note to the command (not executed)

5. Click OK to save.

   

Note: Use the Details tab to set availability, assign a spoken trigger phrase, or restrict the command to a specific application.

For full details, see Commands (Solventum Help Library).

Map device buttons to actions

Device button mappings let you assign microphone buttons or keyboard keys to trigger specific actions in Fluency Direct, such as starting recording, running a command, or sending a keystroke.

To open Device Button Mappings, left-click the Fluency Direct Control Bar and select Device button mappings.

The dialog lists all configured button assignments in four columns:

Column	Description
Device	The physical input device (microphone or keyboard)
Button	The button or key assigned
Action type	The type of action — Recording, Command, or Keystroke
Action	The specific action triggered

Add a device button action

1. Left-click the Fluency Direct Control Bar and select Device button mappings.
2. Click + Add to open the Add a device button action dialog.
3. Click inside the Device button field and press the button or key you want to assign on your microphone or keyboard.
4. Under Action, select one of the following:
   • Recording — Starts or stops dictation. Select a recording mode (Standard, which accepts both text and commands) and a recording behavior (Hold to talk or Toggle to talk).
   • Command — Triggers a Fluency Direct voice command. Start typing to select from the suggestions.
   • Keystroke — Sends a keyboard shortcut (for example, CTRL+S) to the desktop or active window.
5. Click Save.

Tip: Use Hold to talk for short commands or corrections where you want precise control over when recording starts and stops. Use Toggle to talk for longer dictation passages.

Important — Philips SpeechMike field navigation conflict: When you use a Philips SpeechMike with OmegaAI, incorrect Fluency Direct device button mappings can cause the Forward button to skip fields during report navigation. OmegaAI already handles field navigation in the Document Viewer. If the SpeechMike Forward and Rewind buttons are also mapped to Next Field and Previous Field in Fluency Direct, the navigation command is issued twice and the cursor skips past a field.

To avoid this:

• In Fluency Direct Device Button Mappings, remove any Next Field or Previous Field mappings assigned to the SpeechMike Forward and Rewind buttons. Leave field navigation to OmegaAI.
• In Philips SpeechControl, set the SpeechMike to Event mode rather than Keyboard mode, so button presses are passed to Fluency Direct as device events.

For more information, see Device Button Mappings (Solventum Help Library).

Manage your account

The Fluency Direct Control Bar menu provides the following account options:

Change password — Updates your M*Modal account password. Sign out — Signs out the current user from Fluency Direct. Use this when switching users on a shared workstation. Quit — Closes the Fluency Direct application entirely.

Switch accounts or regions without reinstalling

1. Hold Shift and left-click the Fluency Direct Control Bar to open the Advanced Settings menu.
2. Change the base endpoint, account, or location as needed.

Get help and training resources

Left-click the Fluency Direct Control Bar and select Help and training resources for access to in-application help, tutorials, and Solventum support content.

For the full online documentation, visit the Solventum™ Fluency Direct™ Help Library.

Troubleshooting

Issue	Resolution
OmegaAI label not showing on the Control Bar	Confirm the M*Modal browser extension is enabled in Chrome. Refresh all OmegaAI tabs, or log out and back in. Contact your RamSoft representative or Support to confirm the M*Modal license is active for the user.
Cannot log in to Fluency Direct	Credentials are case-sensitive — verify Caps Lock is off. Contact your RamSoft representative or Support to confirm the M*Modal license is active for your account.
Fluency Direct shows Offline or a 404 error	This may indicate a server migration issue. Contact RamSoft Support to verify your account endpoint is correctly configured.
Microphone not detected	Check Windows sound settings. Confirm the correct input device is selected and not muted.
Poor recognition accuracy	Run Profile Training. Confirm Medical Specialty is set to Radiology. Recalibrate the microphone in Microphone Setup.
Extension not in browser list	Install the extension manually from the Chrome Web Store or Edge Add-ons. See Enable the Fluency Direct browser extension.
SpeechMike Forward button skips a field	Remove the Next Field / Previous Field mappings from Fluency Direct Device Button Mappings for the SpeechMike Forward and Rewind buttons. Confirm the SpeechMike is set to Event mode in Philips SpeechControl (not Keyboard mode). See Map device buttons to actions.
Dictation not appearing in Document Viewer	Confirm the cursor is placed inside a report field before dictating. Check that the OmegaAI label is visible on the Control Bar.

Voice commands reference

The following voice commands have been verified to work with the OmegaAI Document Viewer.

Note: OmegaAI also has its own native voice recognition system, separate from Fluency Direct, with its own set of commands. See Voice Recognition and Voice Command Features if you are looking for OmegaAI's built-in voice commands rather than the Fluency Direct commands listed below.

Selection

Command	Alternate phrase(s)	Action
select <word/text>	select all	Selects the specified word, phrase, or all text in the document
select next word	select next sentence / select next paragraph	Selects the next word, sentence, or paragraph from the cursor position
select next <N> words	select next <N> sentences / select next <N> paragraphs	Selects the specified number of words, sentences, or paragraphs forward
select previous word	select previous sentence / select previous paragraph	Selects the previous word, sentence, or paragraph from the cursor position
select previous <N> words	select previous <N> sentences / select previous <N> paragraphs	Selects the specified number of words, sentences, or paragraphs backward
unselect that	unselect text / clear that	Clears the current text selection

Correction

Command	Alternate phrase(s)	Action
correct <word/text>	correct that / correct selection	Opens the correction menu for the specified word or current selection
choose one / two / three...	choose option one / two / three...	Selects a numbered option from the correction menu
spell	spell mode / switch to spell mode / spelling mode	Switches to spelling mode for letter-by-letter dictation

Deletion

Command	Alternate phrase(s)	Action
delete that	delete selection	Deletes the current selection
delete next word	delete previous word	Deletes the word immediately after or before the cursor
delete <N> words	delete next/previous <N> words	Deletes the specified number of words forward or backward
delete sentence	delete current/next/previous sentence	Deletes the current, next, or previous sentence
delete paragraph	delete current/next/previous paragraph	Deletes the current, next, or previous paragraph

Editing and formatting

Command	Alternate phrase(s)	Action
undo that	scratch that / undo command / undo last command	Reverses the last dictation or edit action
cut that	cut selection	Cuts the current selection to the clipboard
copy that	copy selection	Copies the current selection to the clipboard
paste that	paste selection	Pastes clipboard content at the cursor position
lowercase that	lowercase selection	Converts the selected text to lowercase
uppercase that	uppercase selection	Converts the selected text to uppercase
capitalize that	cap that	Capitalizes the first letter of the selected text
all caps on	all caps off / caps on / caps off	Toggles all-caps dictation mode on or off
bold that	bold selection	Applies bold formatting to the selected text
italicize that	italicize selection	Applies italic formatting to the selected text
underline that	underline selection	Applies underline formatting to the selected text

Navigation and scrolling

Command	Alternate phrase(s)	Action
scroll up	—	Scrolls the document view upward
scroll down	—	Scrolls the document view downward
scroll to cursor	—	Scrolls the view to the current cursor position
insert before <text>	—	Moves the cursor to immediately before the specified text
insert after <text>	—	Moves the cursor to immediately after the specified text
new line	next line	Inserts a line break at the cursor position
new paragraph	next paragraph	Inserts a paragraph break at the cursor position
go to beginning of sentence	jump to... / move to... / place cursor at...	Moves the cursor to the beginning of the current sentence
go to beginning of paragraph	jump to... / move to... / place cursor at...	Moves the cursor to the beginning of the current paragraph
go to beginning of document	jump to... / move to... / place cursor at...	Moves the cursor to the start of the document
go to end of sentence	jump to... / move to... / place cursor at...	Moves the cursor to the end of the current sentence
go to end of paragraph	jump to... / move to... / place cursor at...	Moves the cursor to the end of the current paragraph
go to end of document	jump to... / move to... / place cursor at...	Moves the cursor to the end of the document

Field navigation

Important: Field navigation commands work with square bracket [ ] fields, not OmegaAI custom fields.

Command	Alternate phrase(s)	Action
next field	go to/jump to/move to next field	Moves the cursor to the next [ ] field in the document
previous field	go to/jump to/move to previous field	Moves the cursor to the previous [ ] field in the document
first field	go to/jump to/move to first field	Moves the cursor to the first [ ] field in the document
last field	go to/jump to/move to last field	Moves the cursor to the last [ ] field in the document

Target and playback

Command	Alternate phrase(s)	Action
set target	set dictation target / set target window	Sets the active dictation target to the current window or field
clear target	cancel target / remove target / stop using target	Removes the current dictation target
playback dictation	—	Plays back the most recent dictation audio

Punctuation and symbols

Command	Alternate phrase(s)	Action
colon	—	Inserts a colon :
semi colon	—	Inserts a semicolon ;
open parentheses	open paren / left paren / left parentheses / open brackets	Inserts an opening parenthesis (
close parentheses	close paren / right paren / right parentheses / close brackets	Inserts a closing parenthesis )
open quotation	open quote / open quotation marks / open inverted commas	Inserts an opening quotation mark "
period	full stop	Inserts a period .
slash	stroke	Inserts a forward slash /
question mark	—	Inserts a question mark ?
exclamation mark	—	Inserts an exclamation mark !
comma	—	Inserts a comma ,

Related articles

• Voice Recognition and Voice Command Features — OmegaAI's native voice recognition and command system, separate from Fluency Direct.
• Document Editor Overview
• Embedded Document Viewer (EDV)

For topics not covered in this article, refer to the Solventum™ Fluency Direct™ Help Library.