Transcription
Clio Operate has implemented Transcription directly into the platform. This will be available first as part of the Rich Text or WYSIWYG Editor (CK Editor). This means that if you have a Transcription Provider Enabled and set up, you will be able to speak text directly into these fields all around Clio Operate.
As of release v7.10.0, we have rolled out transcription to Voice Notes and the Batch Transcription Workflow Block.

Details
Transcription is supported from v7.9+
From any Blade, Comment Field, Wiki, and more, so long as you are in a Rich Text Editor (one of those boxes with text and formatting controls, such as in the screenshot above). If your environment has a Transcription provider installed and configured, you will see this microphone icon. The button won't be visible if you don't have a provider installed and configured. If it's something you can't see, but think you should, contact your own internal Clio Operate Administrator.
When you first click the microphone icon, you may need to give the browser permission to access the microphone. If you already use the Voice Notes feature in Clio Operate, you may have done this in the past, and the microphone will activate straight away.
If not, you will see a dialogue box like this.

Decide whether you want to give access to the microphone just this time or whenever you use Clio Operate. Once you've done that, the microphone should activate. This is indicated by the microphone icon pulsing. As soon as this has happened, the microphone is active.

You will briefly see a Blue Information Box warning you that the Microphone is active and transcription is in progress. This will fade after a second or so.
Once you're finished, pause for a second or two before deactivating the microphone button and closing the connection. Different providers process the text differently, and you may notice that once paused, it applies some slight formatting and corrects punctuation or any mistakes it finds. This is the benefit of AI-powered transcription tools: once you finish, they get a sense of the context and use that to improve transcription accuracy.
Available Providers
From day one, Clio Operate will launch with two Transcription providers, though we may add others in the future.
| Provider | Name | Website |
|---|---|---|
|
![]()
|
Speechmatics | https://www.speechmatics.com/ |
![]() |
Azure Speech SDK | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-sdk |
Clio Operate operates both of these providers in a BYOL (Bring Your Own Licence) format, meaning you can register for the service and the package/tier of your choice, and then simply enter your credentials to get going once installed.
How to get it
To get started with one of these product plugins, contact your Clio Operate CSM and let them know which provider you would like to install.
- Visual Workflow blocks for managing batch transcription through a 3rd party provider.
- Configuration on Related Documents to allow for the workflow to be called on relevant (i.e. voice note) documents.
- Configuration of the voice note playback screen to allow for viewing and editing completed transcriptions, and for providing an indication of the last edit made.
- Audit Logging on voice notes to record when a recording/transcription is requested, opened, edited, or downloaded.
Transcribing a voice note
You can transcribe a voice note recording without leaving the matter. This works on new, historical, and uploaded recordings.
Record a voice note as usual, then find the recording in the Related Documents section of the work item. Hover over a recording to reveal its controls: Play, Download, Generate Transcription, and View Transcription.
- If the recording has not been transcribed, select Generate Transcription. Transcription runs only when you select it, so you do not run up provider costs unnecessarily.
- Once a recording has been transcribed, use View Transcription to open it.
Selecting View Transcription opens the transcription in its own blade, titled with the recording's file name. The audio player sits at the top of the blade, with the transcribed text shown in an editable box below it, so you can play the recording back while you read and correct the text. The blade also provides Download, Save, and Save & Close.
When you change a transcription and save it, an indication of the most recent edit is shown, and all edits are stored for audit.
Using the transcription workflow
For batch transcription, Clio Operate provides a set of workflow blocks. These let a workflow pick up an audio file from the document store, send it to your provider, and save the result back against the related document. Because longer recordings are processed in the background, the workflow starts a job and then completes it once the provider signals that the transcription is ready.
The following blocks are available in the workflow toolbox, under the Transcription category:
| Block | What it does |
|---|---|
| Start Transcription Job | Begins a transcription job with the provider. |
| Monitor Transcription Job | Checks the current status of a transcription job with the provider. |
| Complete Transcription Job | Retrieves the completed transcription and updates the related document. |
| Cleanup Transcription Job Post Completion/Error | Removes any media that is no longer needed once the job completes. |
| Transcription Error | Handles errors that occur during transcription. |
The transcription output is saved back to the document store as a .txt or .rtf file.
Transcription data in Data Composer
Transcription details are exposed in Data Composer, so you can use them elsewhere on the platform, for example, in workflows and document templates. These include whether a recording has been transcribed, the date and time it was transcribed, the transcription content and its identifier, the length of the recording, and whether the transcription has been overridden, by whom, and when it was last modified. [field list to verify]
Azure Speech SDK
Transcription is a feature of the Clio Operate platform that enables quick, easy speech-to-text conversion across several Clio Operate functions. The Transcription article provides more information about using this functionality.

Provider
Azure Speech is one of the available providers for the Transcription Functionality in the Clio Operate platform. This functions on a BYOL (Bring Your Own Licence) basis. We recommend you check out their website and trial their service before committing. Once you're happy and have an agreement, tier, contract or package in place, you will be able to use your credentials to set up Azure Speech as a provider in Clio Operate.
You can find more about Azure Speech on the Microsoft Learn site. You can register for an account and get credentials from the Azure Portal.
Installation
To have Azure Speech installed in your Clio Operate environment, you must be on version 7.9.0 or later.
Reach out to your CSM, and they will install the latest version of the plugin for you. Initially, in a non-production environment for you to test, and then in production.
Configuration
Configuring a transcription plugin involves two steps.
- Configuring the Global Feature.
- Configuring a Linked Service for authentication.
Global Feature Config
- Navigate to Modeller > Global Features
- Then search for the transcription Feature.
- Ensure the checkbox is enabled, then click the green cog to open the configuration blade.
- On this screen, you have a drop-down to choose the provider (if you have more than one provider installed), choose Azure Speech Service.
- Next, the Global Feature will check to see if there is a matching Linked Service and whether it is configured correctly. This Message will be red, amber, or green.
- Red - No Linked Service found.
- Amber - Linked Service exists, but some fields are missing or incorrect.
- Green - Everything looks good, and is working as expected.
- You can configure the Linked service directly from the button on the Global Feature blade, but we'll come back to that shortly.
- Set the Multi-channel audio option using the Enable Multi-channel Audio toggle. Leave this off unless you need to transcribe separate audio channels independently.
- For now, you need to select your Azure Region and the Speech Recognition Language.
Please consult your IT Administrator, or whoever will be providing your API Key, as they will be able to let you know which Azure region to select.
In our case, we created our API Key in the uksouth Azure Region and are operating speech recognition in English, specifically en-GB from the ISO 639-1 list of language codes. - If you will use batch transcription (for example, transcribing voice notes through a workflow), complete the Azure Blob Storage Configuration. This storage holds audio files while they are transcribed. Consult your IT Administrator for these values.
- Azure Blob Storage Base Url - the base URL of your blob storage account.
- Azure Blob Storage Container Name - the container used for transcription files.
- Azure Blob Storage SAS Token - the shared access signature token that authorises access to the container.
- Don't forget to Save & Close the Global Feature.
Linked Service Config
Next, we need to configure the Linked Service. If you are still on the Transcription Global Feature Blade, you can click Configure it. Otherwise, you can navigate to Admin > Integrations > Manage Linked Services.
- Look for a service called Azure Speech Service.
-
You can create it by clicking the Green Add New icon in the top right-hand corner if it doesn't exist.
- Then, choose Shared secret from the list of available service providers.
- You will need to populate the following fields:
| Field | Value |
|---|---|
| System-name | azurespeechservice |
| Name | [No Specific Value] Azure Speech Service |
| Icon | [No Specific Value] We use ‘fa-microphone’ |
| Description | [Optional] |
| Secret | {Your own API key} |
| Allow fallback to system secret | Yes |
| API Base URL |
This will be based on the Azure region, your API Key is for https://{azure-region}.api.cognitive.microsoft.com |
| HTTP Header to send token in | Ocp-Apim-Subscription-Key |
- Fields in Bold are mandatory.
- Fields with [No Specific Value] can be set as you please.
- Secret must be populated with your own API Key.
- Make sure you update the API Base URL with the region for which your Azure Speech subscription is set up.
Once you're done, hit Save & Close. Then, navigate back to the User side of Clio Operate, and you can test it out in any Rich Text Field.
Speechmatics
Transcription is a feature of the Clio Operate platform that enables quick, easy speech-to-text conversion across several Clio Operate functions. The Transcription article provides more information about using this functionality.

Provider
Speechmatics is one of the providers available for transcription functionality on the Clio Operate platform. This functions on a BYOL (Bring Your Own Licence) basis. We recommend you check out their website and trial their service before committing. Once you're happy and have an agreement, tier, contract or package in place, you will be able to use your credentials to set up Speechmatics as a provider in Clio Operate.
You can find more about Speechmatics and register for an account on their website.
Installation
To have Speechmatics installed in your Clio Operate environment, you must be on version 7.9.0 or later.
Reach out to your CSM, and they will install the latest version of the plugin for you, initially in a non-production environment for testing, then in production.
Configuration
The configuration of a transcription plugin involves two steps: the Global Feature and a Linked Service for authentication.
Global Feature Config
- Navigate to Modeller > Global Features
- Then search for the transcription Feature.
- Ensure the checkbox is enabled, then click the green cog to open the configuration blade.
- On this screen, you have a drop-down to choose the provider (if you have more than one provider installed), choose Speechmatics.
- Next, the Global Feature will check to see if there is a matching Linked Service and whether it is configured correctly. This message will be red, amber, or green.
- Red - No Linked Service found.
- Amber - Linked Service exists, but some fields are missing or incorrect.
- Green - Everything looks good, and is working as expected.
- You can configure the Linked service directly from the button on the Global Feature blade, but we'll come back to that shortly.
- For now, you need to make sure you enter the:
-
Socket API URL: In our case, this was
wss://eu2.rt.speechmatics.com/
For now, it looks like all Speechmatics Customers use the same URL, but this could change in future. Please consult the Speechmatics Documentation.
-
Socket API URL: In our case, this was
- Don't forget to Save & Close the Global Feature.
Linked Service Config
Next, we need to configure the Linked Service. If you are still on the Transcription Global Feature Blade, you can click Configure it. Otherwise, you can navigate to Admin > Integrations > Manage Linked Services.
- Look for a service called Speechmatics.
- If it doesn't exist, you can create it by clicking the green Add New icon in the top right-hand corner.
- Then choose Shared secret from the list of available service providers.
- You will need to populate the following fields:
| Field | Value |
|---|---|
| System-name | speechmatics |
| Name | [No Specific Value] Speechmatics Service |
| Icon | [No Specific Value] We use ‘fa-microphone’ |
| Description | [Optional] |
| Secret | {Your own API key} |
| Allow fallback to system secret | Yes |
| API Base URL | https://mp.speechmatics.com |
| HTTP Header to send token in | Authorization |
| HTTP Header Prefix | Bearer |
- Fields in Bold are mandatory
- Fields with [No Specific Value] can be set as you please
- Secret must be populated with your own API Key
Once you're done, hit Save & Close. Then, navigate back to the User side of Clio Operate, and you can test it out in any Rich Text Field.

