Skip to content
  • There are no suggestions because the search field is empty.

Step 4: Translation - How do I enable Translation for my Service using the new UI?

Learn how to enable AI Text & Audio Translations for your Service using the New Services UI.

In this step, you will configure the AI text and audio translation settings for your Service. If you don't need translations, you can skip this step and proceed directly to Step 5 - Output. For a list of all steps see our Service Wizard Steps below.

Add Translation

To begin, click the Add Translation option and select the language you want to add from the dropdown. You can add multiple languages to make your content accessible to a wider audience.


Each translation added will appear in the list with the following details:

  • Language - Displays the selected output language for the translation
  • Translation Engine - Indicates which AI provider is being used for translation.
    Common engines include OpenAI, Google, Amazon, DeepL, Nova, Soniox and Gemini 
  • Output Type - Displays whether the translation will be used for Subtitles or Dubbing. You may enable one or both.
  • Settings Icon - Opens advanced settings for that translation. This is where you can change the translation engine and enable dubs.
  • Delete (×) - Removes the selected translation from the list.

Advanced Settings: Additional configuration options are available in the Advanced Settings section. Details about these optional settings are listed below.

NEXT STEP: Once you’ve entered the required information, click "Continue" to move to Step 5: Outputs for HLS, SRT, RTMP or CMAF where you will choose the output for your Service.

Navigation Options

At the bottom of the screen, you will see the following actions:

  • Cancel - Cancels the creation of your Service and exits the wizard.
  • Reset - Clears all fields and settings in the Wizard so you can start over.
  • Step Back - Returns to the previous step if you need to modify earlier settings.
  • Continue - Moves to the next step of the wizard once the required fields are completed.

NOTE: If you click off the Wizard without Resetting or Canceling your inputs will be saved and you can return to complete the setup later.

Your Service is not created until you have been through all 6 steps and clicked the "Create Service" button.

Advanced Settings

To access the Advanced Settings, click the Settings option. This modal allows you to manage translation-specific settings for AI-generated subtitles and dubbing.

Subtitles

When you select Subtitles in the Translation Settings modal, you can configure how text-based translations are generated and displayed.

Language: This field shows the target translation language you have selected. If multiple variants are available, you can choose the preferred variation for your subtitles.

Translation Engine: Select the AI engine that will generate subtitle translations. Different engines may offer varying accuracy, tone, and context handling. 

Glossary: Use the Glossary option to include a predefined set of terms or phrases for translation consistency. You can select an existing glossary or choose Not set to proceed without one. Read more about Glossaries here.

NOTE: Only glossaries that have been created and saved in your account will appear in the dropdown list.

Save Subtitle Changes

Once you have configured your subtitle settings:

  • Click Update Translation to save your settings.

  • Click Cancel to exit the modal without saving.


Dubbing

When you select Dubbing in the Translation Settings modal, you can configure how translated audio output is generated.


Enable Dubbing: Toggle Enable Dubbing to turn on AI audio generation for the selected translation language. When enabled, you can configure additional voice and playback options for the dubbed output.

Dubbing Mode: Choose how AI voices are used in your dubbed translation.
There are three available dubbing modes: Single Voice, Dynamic Voice and Cloned Voice.

Single Voice

Select Single Voice to use one consistent AI-generated voice across the entire translated audio track. This option provides a uniform tone where speaker differentiation is not required.

Confirm or change the following five options:

  • Dialect - Select the Dialect that best matches your audience. Some languages will have more than one dialect available.

  • Gender - Select the preferred voice gender for the AI dubbing output.

  • Speaker - Choose a specific voice model for your dubbed translation. Not all languages have more than one option. You can preview available voice samples by clicking the speaker icon next to the voice name.

  • Speaking rate - Set the Speaking Rate to control how fast or slow the AI voice delivers the translation. The default is set to Auto which is a Dynamic Speaking Rate: Automatic detection and syncing of dubbed voices to match the timing of the source language. You can change the speaking rate, lower values speak slower and higher values speak faster.

  • Original Audio Volume - Use this slider to adjust how much of the original audio remains audible in the background. This setting controls the mix ratio between the original audio source and the dubbed track in the final output.

Dynamic Voice

The Dynamic Voice mode automates dubbing for multiple speakers in your content. When selected, the system automatically selects the best voice for each speaker, matching tone and gender, for a more natural and engaging listening experience.

Cloned Voice

The Cloned Voice mode delivers the most natural and lifelike dubbing experience by replicating the tone, emotion, and speaking style of each original speaker in the translated voice. This option is ideal when you want to preserve the character and delivery of the original dialogue while translating it into a different language.


IMPORTANT: 

For both Dynamic Voice and Cloned Voice, the following settings are required:

  • ASR Engine: Speechmatics (with diarization enabled)
  • Translation: Gemini

If you had a different setup, it will automatically switch to the above settings when you select Dynamic Voice or Cloned Voice.

If you switch back to the Single Voice option, the settings will not revert to their previous selections. You will need to manually reselect your preferences again.

Dialect: Select the regional dialect that best matches your target audience. Available dialects vary by language (e.g., Spanish (Spain), Spanish (Latin America)).

Original Audio Volume: Use the slider to control how much of the original audio remains audible beneath the dubbed track.

  • Set to 0% for dubbed audio only with no original audio

  • Set to 100% to keep the full original audio with dubbed audio layered on top

  • Values in between create a mix of both

     

Voice Isolation + Background Audio Mix: When enabled, this feature separates the original speaker's voice from background sounds (music, ambient noise, sound effects) and overlays only the dubbed voice on top of the preserved background audio. This creates a more natural listening experience by maintaining the original atmosphere while replacing the speech.

Extra Prompt: Enter additional instructions for the AI translator. Use this field to guide translation style, terminology preferences, or specific handling of content. For example:

  • "Avoid profane language in translated output"

  • "Write out numbers, abbreviations, and acronyms the way they should be said out loud"

  • "Use formal language throughout"

  • "Maintain technical terminology in English"

NOTE: Extra Prompt is only available for Dynamic and Cloned Voice options

 

Save Dubbing Changes

Once you have configured your dubbing settings:

  • Click Update Translation to save your settings.

  • Click Cancel to exit the modal without saving.

 

 

Service Wizard Steps

Step 1 - General
Step 2 - Input Media - HLS, SRT, RTMP or CMAF
Step 3 - Transcription
Step 4 - Translation
Step 5 - Output - HLS, SRT, RTMP, CMAF or 608
Step 6 - Preview