Enabling verbal time entry

Verbal time entry allows users to record a spoken description of their work in Legalsense. Legalsense sends the recording to a configured AI provider, then creates draft time entries for review and approval.

This article explains what is needed to enable verbal time entry for your organization. Your role as an administrator is to make the necessary preparations, obtain an API key from an AI provider, and request setup through Legalsense Support.

Verbal time entry is available starting with Release 26.04.

Before you start

Before contacting Legalsense Support to enable verbal time entry, make sure you have addressed the following:

Internal decision on data processing. Using verbal time entry means that audio recordings and contextual data from your Legalsense environment are sent to an external AI provider for processing. Make sure your organization has decided that this is acceptable. See the section What data is shared with the AI provider for details on what is sent and how it is handled.
An API key from your AI provider. See below. In order to configure the AI provider in Legalsense, you need to be an Admin user.

Once you have both of these in order, you can configure the AI provider yourself. Finally, contact Legalsense Support to enable the voice recorder and then you're ready to go!

AI providers

In order to configure an AI provider in Legalsense, you need to be an Admin user. Visit the page under Settings → Integrations → AI provider to perform the set-up.

OpenAI

Legalsense uses OpenAI's transcription and language models to transcribe submitted audio into text and then convert that text into structured time entry data.

To obtain an API key, visit https://platform.openai.com and create an account with payment details. When creating the API key, make sure it has read and write access to at least the Responses, Chat completions, and Transcription (Audio API) endpoints. Alternatively, you can set up a service account as an OpenAI API user. This is preferred if multiple users will be using the feature.

Azure OpenAI

Azure OpenAI is available as a provider starting with Release 26.06. If your organization already runs on Microsoft Azure, you can point Legalsense at your own Azure AI Foundry resource instead of plain OpenAI. Verbal time entry then runs through your existing Azure billing, security, and compliance posture. The data Legalsense sends is identical to the OpenAI setup; see What data is shared with the AI provider.

This requires an Azure AI Foundry resource with two model deployments: one for transcription and one for structured output. When you select Azure OpenAI as the provider, you provide:

Resource endpoint: the base URL of your Azure resource, for example https://your-resource.cognitiveservices.azure.com/.
API key: a key for that resource.
Transcription deployment name: the name of your deployment of GPT-4o-transcribe or GPT-4o-transcribe-mini.
Structured-output deployment name: the name of your deployment of GPT-4.1 or GPT-4.1-mini, or an equivalent model. The GPT-5 series is not yet supported.

Deployment names are not validated when you save, so make sure they match exactly what is configured in Azure, and that each deployment uses one of the supported models above. If a name or model is wrong, verbal time entry will fail or perform poorly at processing time rather than at setup.

What data is shared with the AI provider

When a user submits a verbal time entry, Legalsense sends the audio recording to the configured AI provider for transcription and interpretation.

To help the provider match the spoken input to the correct matters, activities, and timekeepers, Legalsense also sends contextual information about the user's accessible work. This contextual information is always bounded by what the user can access: it cannot cross permission or Chinese wall boundaries. In other words, only the information that a user can see in the manual time entry form is included. At the time of writing, this comprises:

Names and IDs of:
- active timekeepers (including the submitting user),
- time-writable matters,
- activities for those matters,
- submatters for those matters, and
- Recofa categories for those matters.
The audio recording submitted by the user.

OpenAI data handling

At the time of writing, data processed via the OpenAI API is not used to train OpenAI's models. OpenAI's API privacy statement can be found at https://openai.com/enterprise-privacy/.

Legalsense sets the store=False parameter for applicable endpoints, which means OpenAI does not retain prompt data by default. If your organization requires additional data controls, such as data residency or zero data retention, you can request these from OpenAI. More information is also available at https://developers.openai.com/api/docs/guides/your-data.

Permissions and user access

For a user to use verbal time entry, they need:

Access to the Timesheet page (requires permission to view and create a time entry).
Permission to view and manage their own draft time entries.

In most environments, users who can already write time will have the necessary permissions by default. If certain users cannot see or use the Voice tab after setup, contact Legalsense Support to verify their permissions.

In addition, the user must have a microphone and use a supported browser: a recent version of Chrome, Firefox, or Safari.

Troubleshooting

The AI provider configuration is not working

If an error occurs when configuring the AI provider, check the credentials for the selected provider:

OpenAI: the most likely cause is an API key that is invalid, has insufficient permissions, or belongs to an account without payment details. Verify the key and the account setup at https://platform.openai.com.
Azure OpenAI: check that the resource endpoint and API key are correct for your Azure resource.

Note that the health check confirms credentials and connectivity, but does not run a full end-to-end voice-to-time submission. If setup succeeds but verbal time entry does not work or performs poorly, check that the correct models are deployed: for Azure OpenAI, confirm that the transcription and structured-output deployments point at the supported models listed under Azure OpenAI.

Users see the Voice tab, but cannot record

If a user reports that the microphone button is greyed out, check the following:

The user may not have permission to manage draft time entries. Contact Legalsense Support to verify.
The user may not be using a supported browser. Ask them to try a recent version of Chrome, Firefox, or Safari.
The user's browser may not have microphone permission for Legalsense. Ask them to check their browser settings and allow microphone access for your Legalsense domain.

Users submit recordings but no drafts appear

A short processing delay of 10–60 seconds is normal. If drafts consistently fail to appear after waiting, it may indicate a problem with the AI provider configuration or connectivity. Contact Legalsense Support and provide the approximate time of the failed submission so it can be investigated.