System Configuration
Enabling Transcription Service
To enable transcription service, the system administrator needs to configure the following:
- Transcription Engine
- Processing Queue
- Transcription Job
Configuring Transcription Engine
Navigate to Administration > Speech Analytics > Transcription > Engines and click Add to create a new transcription engine.
Select the desired transcription service provider and configure the required settings, such as API keys, region, etc.

After adding the engine, test the connection by clicking the Test Connection button. A sample audio file is sent to the transcription service, and the transcribed text is returned and displayed.

Configuring Processing Queue
Navigate to Administration > Jobs > Processing Queues and click Add to create a new processing queue for transcription jobs.
Select:
- Scope: Global
- Record type: Call
- Populate queue with events: Call - recording finished

With this configuration, audio recordings are added to the processing queue as soon as the call recording finishes.
Note
With the global scope, records from all tenants are added to the processing queue, including tenants without transcription enabled. The transcription job (configured next) filters and processes only records belonging to tenants and users with transcription enabled.
Configuring Transcription Job
Navigate to Administration > Speech Analytics > Transcription > Job Definitions and click Add to create a new transcription job.
Select the following settings:
- Access scope: Unrestricted - All tenants, including System
- Data source: Incremental using queue
- Source queue: Select the processing queue created earlier
- Transcription engine: Select the transcription engine created earlier

Under Filtering Criteria, configure the following filters to ensure that only the records belonging to tenants (and users) with transcription enabled are processed:
- User - License is Speech analytics license
- Call - Duration between 0:15 and 2:00:00 (15 seconds to 2 hours)
Note
The job sources data from the processing queue and applies filters to discard records that should not be transcribed—specifically, those not belonging to users with the transcription license.
Tip
The duration filter is optional but recommended to avoid transcribing very short calls (less than 15 seconds) or very long calls (more than 2 hours).

Under Action after successful processing, optionally configure the job to send transcribed records for further processing, such as AI Assistant tasks (call summarization, topic analysis, etc.).
- Publish to queue(s): Select the target processing queue(s).

Finally, under Schedule section, select:
- Run this job: Continuously
With this setting, the transcription job runs automatically as new records are added to the processing queue.
