What's new

We have added new AI features to improve the user's daily work. These include the ability to automatically add punctuation to transcripts, different types of summaries from simple to detailed, and advanced insights.

Send dictations to SpeechLive AI

We have further extended our speech recognition offering by providing users with the ability to integrate with Nuance Dragon Medical One. This enables users to send dictations directly from SpeechLive to Dragon Medical One (DMO), improving their daily workflow. This means that SpeechLive users can now choose from an even wider range of speech recognition contexts, depending on their needs and preferences.

Set up Dragon Medical One integration

Send dictations to Dragon Medical One

After adding the sidebar for typists, we have now added the same feature for authors. This provides authors with a quick overview of all their pending dictations and which typist or team they are assigned to. This also gives the author a better idea of how many of their dictations are still being processed and the total length of their pending dictations.

Sidebar for authors

This new option allows authors to see the total workload of a team in the sidebar. This means that the author can also see the duration and number of dictations assigned to a team by other authors. With this information, authors can better assess the total workload of a team and how long it will take to process their own dictations.

Activate the total workload view for authors

Total workload view

The mobile app already offered a fast forward/rewind as well as the jump to the beginning/end function. To further improve the user experience, we split these functions into separate buttons. This not only prevents accidental use of the wrong function, but also saves the user time by allowing them to access the desired function with a quick tap of a dedicated button. The new winding speed option allows the user to customize the fast forward/rewind buttons and how many seconds they jump forward/back in the dictation.

Rewind and Fast forward

Already available for the Web App, we added the option to select the number of speakers when sending a dictation to SpeechLive speech recognition. This allows mobile users to select the number of speakers of their dictation on their mobile phone and receive a transcript with timestamps of the different speakers.

When using real-time speech recognition, users can now add their own personal vocabulary. This feature ensures that any special vocabulary or names are correctly interpreted when using speech recognition.

Add words to the vocabulary

We have also made a number of small improvements to the user experience to help users in their day-to-day work. These include visual indicators when some of the dictation properties are mandatory fields. We have also added the option to make the due date a mandatory field. Another improvement is a warning message to the user when activating an overwrite recording mode to prevent accidental deletion of previously recorded dictations.

Administrators can now install the SpeechLive Desktop App for multiple users at the same time. This saves them a lot of time when rolling out the Desktop App in their organization, especially for larger groups of users.

When using real-time speech recognition, users can now add their own personal vocabulary. This feature ensures that any special vocabulary or names are correctly interpreted when using speech recognition.

Add words to the vocabulary

Users can now add their own custom voice commands. This allows them to define commands for content they frequently reuse. For example the address of their company, standardized letter headers, signatures, contact details, disclaimers or standard responses. This feature greatly enhances the speech recognition function and commands are additionally used across all applications (Web, Mobile and Desktop), ensuring the same speech recognition experience across multiple devices.

Add custom voice commands

Users can now split up longer dictations into smaller parts. This is especially helpful for longer dictations to split up the workload better between different typists.

Split dictations

	Note
	This function is only available for SpeechLive Enterprise.

Typists can now turn on in-app sound notifications for new dictations. They can also set notifications for specific dictation priorities so that they only receive notifications for their most important work. This feature greatly improves typists' day-to-day work by ensuring they are notified as soon as new dictations are ready to be processed.

Notifications for new dictations

Users can now create new dictations or speech recognition sessions by simply entering a specific URL deep link. They can even add additional parameters to the URL to pre-populate specific dictation properties, such as work type, dictation priority and more. This saves authors a lot of time in their daily work, especially when they use very similar dictation properties. At the same time, it is now possible to open a specific dictation directly by typing the correct URL in the browser's address bar.

Create new dictations via URL deep link

Administrators can now pre-configure the Mobile App via Unified Endpoint Management (UEM) and Mobile Device Management (MDM) to force users to use biometric or PIN authentication. This ensures a secure rollout of the app within organizations, providing additional protection for sensitive data.

Users can now add their own custom voice commands. This allows them to define commands for content they frequently reuse. For example the address of their company, standardized letter headers, signatures, contact details, disclaimers or standard responses. This feature greatly enhances the speech recognition function and commands are additionally used across all applications (Web, Mobile and Desktop), ensuring the same speech recognition experience across multiple devices.

Add custom voice commands

Users can now add their own custom voice commands. This allows them to define commands for content they frequently reuse. For example the address of their company, standardized letter headers, signatures, contact details, disclaimers or standard responses. This feature greatly enhances the speech recognition function and commands are additionally used across all applications (Web, Mobile and Desktop), ensuring the same speech recognition experience across multiple devices.

Add custom voice commands

Typists can now quickly manage all their dictations from a in-tray on the left side of the dictation list. This sidebar contains a list of all authors and teams the typist is connected to. In addition, they can see the workload, i.e. the total number of dictations per author and the total length of all dictations, and this information is updated in real time. To free up screen space, it's possible to collapse the sidebar.

How to use the sidebar

SpeechLive already uses auto-refresh, which means that the dictation list is automatically updated periodically. This has now been enhanced to provide an even better, real-time, event-based auto-refresh. This means that whenever a dictation is changed or a new dictation is added, the dictation list as well as the new sidebar reflect these changes in real time.

We already provided the average turnaround time for different typists, and now we have added even more nuanced data to the reports: You can now review the total minutes for specific typists' turnaround time, showing the cumulative amount of time it took each typist to process dictations. The .CSV exports now include whether dictations were picked up and finished by a different typist.

We have improved the design of the mobile app to be more in line with the new Web App. But it is not just about the design, we have also improved the most important functions. For example, it is now possible to start a new dictation or speech recognition with a single click, and other functions such as downloading a transcript or changing properties now require fewer clicks.

Users can now cut and delete specific parts of a dictation to further edit their dictations. Together with the existing editing options, this further helps users to create dictations quickly and easily on the go.

Trim

Users can now share dictations as well as attachments and transcripts with iManage. This greatly improves the daily workflow of larger organizations that integrate SpeechLive into their existing document management structure. We have also added an Integration subtab that allows administrators to enable/disable integrations with other applications.

Set up iManage integration

Share dictations and attachments with iManage

	Note
	This function is only available for SpeechLive Enterprise.

Users can now attach additional file types to their dictations like PDFs, PowerPoint presentations or Excel sheets. This allows users to utilize different file types they use in their daily work and to add additional information and context to their dictations.

We have improved the performance of the dictation list, including loading times and overall stability. When opening dictations, attachments are now loaded when scrolling, which also improves the opening time of dictations.

We added a new item to the personal settings of the user: Archive immediately. If activated, dictations set to finished are automatically archived immediately.

Archive immediately

This setting can also be configured for all workflow users by the account administrator, making it more convenient for administrators to quickly set the archive settings for all their workflow users.

Auto archive settings

Filters set up by the user in the dictation list are now saved even when the user signs out and in again. This saves a lot of time on the daily work, enabling users to customize their dictation list and have it immediately ready as needed.

Filters are also saved based on the view, so if the user sets different filters for the archive than those are saved independently, the same is true for office managers when using the all dictations view.

Filter and sort dictations and customize dictation list

Account administrators and office managers are now able to export a list of all workflow users. This list can also be re-imported, saving the administrators time when editing users, especially in organizations with a large number of workflow users.

Bulk user export

Account administrators and office managers can now export the user relationships. This allows for a different method to view the relationship between the different workflow users and get a quick overview of the relationships.

Export user relationships

We improved the tooltips for the quick filter, helping the users to quickly get an overview which dictations are filtered by the respective option.

When using SpeechLive speech recognition for the first time, the language is selected based on the browser language. If the user changes the language, the selection is saved for the next time.

We improved the error message when connecting a SpeechMike in an unsupported button mode. This includes a link to the help with more information on how to set the device to the correct button mode.

Authors did not receive emails when dictations were transcribed.

The recorder froze when the browser was not in focus.

When the SpeechLive window is in focus, users can use their keyboard to control the web player as it was already available in the legacy Web App.

Hotkeys

When using hardware with SpeechLive its necessary to connect the hardware manually with a few clicks. However, when installing Philips Device Connector (PDC), users no longer need to perform those manual steps. We added an installation wizard, to guide the users through all the necessary steps to install PDC and improve the experience when using hardware with SpeechLive.

The newly introduced pop-out player is now also supported on the Microsoft Edge browser, which means it is now available for all supported browsers.

Use the pop-out player

We improved the structure of the sign in credentials for the DragonBar. This only influences new users.

Install and use the DragonBar

We have added a new feature to the dictation properties area. When creating a dictation, users can activate the keep property values checkbox. After activating the checkbox, the dictation properties entered will be reused the next time the user creates a dictation. This saves users a lot of time in their daily work, as they no longer have to enter all the values manually, but only change the ones they need.

Keep property values

When starting a new dictation or opening a dictation, the recording mode is now displayed on the record button. This allows users to quickly see which recording mode they are currently using.

The pagination did not reset to page 1 after applying new filters.

Users can no longer record in multiple tabs simultaneously.

We improved the bulk delete function for typists by providing more information in some cases.

We removed the "Not equal" option for event based rules; when creating event rules, users can now only select "equals" state.

When playing back dictations, users are now able to switch to a small extra pop-out window that stays on top. This makes it even easier to transcribe dictations and move the player where needed and takes up much less screen space.

Use the pop-out player

We added support for Dragon Legal Anywhere, Dragon Professional Anywhere and Dragon Law Enforcement (North America only). This allows users to send dictations to Nuance's speech recognition servers and receive a transcribed document along with the original audio. This further enhances the speech recognition offerings in SpeechLive and allows users to have more choices when it comes to speech recognition.

Purchase speech recognition

Activate speech recognition for users

Account administrators can now set up specific rules to automatically reassign dictations. Those rules can be time or event based. For example, dictations in the transcription pending state are automatically reassigned to a different team. This also includes keyword-based routing of dictations, e.g. based on the work type or custom fields. These automatizations greatly reduce the workflow tasks for the administrator and cause less overhead buy automatically reassigning unprocessed dictations. Rules are only available for SpeechLive Enterprise.

Set up event rules

Set up time rules

Account administrators can now set dictation properties on a global level in the Web App, this means that those settings are also used in the Mobile App. It allows admins to control the values available for various dictation properties, e.g. Work type, Category, Department and more. Organizations can use this feature to ensure that the same information is entered by all users, ensuring consistent use of dictation properties across the whole organization.

Preset dictation properties

Authors can set a preferred typist/team and this setting is now also synchronized across all platforms, it applies to the Web App, Mobile App and Desktop App. SpeechLive Enterprise customers can additionally also set an alternative typist/team.

The account administrator can also preset this setting for each user in the Web App, ensuring that dictations are always assigned to the correct typist or team.

We improved the customization function of the dictation list table to make it clearer which columns are visible or hidden. In addition, users can now reset the view to the default settings or make all columns visible with a single click.

Customize the dictation list

We improved the performance of the reporting tab of SpeechLive, decreasing the loading times as well as increasing the process times. This ensures that users will get the information even quicker, helping them to allocate resources more efficiently.

When a dictation is set to finish by the typist, the dictation is now automatically closed. This saves the user an extra click, improving their daily workload.

The last selected language is now saved when using speech recognition.

After reassigning dictations, it was not possible to add attachments.

Users can now send dictations to Dragon speech recognition from within the app.

Account administrators can now set dictation properties on a global level in the Web App, this means that those settings are also used in the Mobile App. It allows admins to control the values available for various dictation properties, e.g. Work type, Category, Department and more. Organizations can use this feature to ensure that the same information is entered by all users, ensuring consistent use of dictation properties across the whole organization.

Authors can set a preferred typist/team and this setting is now also synchronized across all platforms, it applies to the Web App, Mobile App and Desktop App. SpeechLive Enterprise customers can additionally also set an alternative typist/team.

The app triggers the newly introduced event as well as time-based rules (SpeechLive Enterprise only).

If custom columns have been renamed in the Web App, those values are now also displayed in the Mobile App. This ensures that additional information is correctly added to dictations by all users.

Authors can set a preferred typist/team and this setting is now also synchronized across all platforms, it applies to the Web App, Mobile App and Desktop App. SpeechLive Enterprise customers can additionally also set an alternative typist/team.

The app triggers the newly introduced event as well as time-based rules (SpeechLive Enterprise only).

For some users, if the browser window was minimized when recording with hardware devices, the recording was lost.

Video files were not attached correctly for typists.

Fixed some errors when bulk importing users.

Auto logout did not work correctly for some users with a foot control.

Typists were unable to send dictations to the transcription service.

When uploading a dictation, the file name is preserved.

The mac version of the Desktop App now also supports automatic updates. Users still need to manually update to version 3.5.8, future versions will now be updated automatically.

Users are now actively asked to grant accessibility permission to use the app. This step is necessary to use the dictate at cursor function of the app.

Corrected an error when assigning a speech recognition package to a user.

We improved the reliability of the send to speech recognition function.

Improved and provided the correct error message for failed dictation uploads.

Removed a duplicated loader indicator on longer dictations.

We fixed some issues when changing the settings of the foot control.

You can now close the app from the dock.

The app no longer blocks clicks to other windows behind the app.

You can now move or close the sign in screen.

When automatically uploading dictations from an external device and using the delete after upload feature, dictations weren't always deleted.