Voice acting

Voice acting is used to capture a real actor’s performance — including intonation, rhythm, and emotional delivery — and transfer it to synthesized voices while keeping the original timing.

Voice acting is available:

  • as an enhancement option inside Lip-sync tasks, and

  • as a standalone Voice Acting task.

Voice acting can be used when working with the following voice types:

Supported for:

Not Supported:

  • A-tier

  • B-tier, C-tier

  • Special voices

  • S-tier

  • Voice cloning

  • Emotional Transfer

  • Languages: Hungarian, Norwegian, Vietnamese

Important notes

  • The voice actor’s voice is not cloned and is not reused elsewhere.

  • The purpose of this task is to reproduce:

    • intonation

    • acting style

    • emotional delivery

    • accent

    • lip-sync timing and body language cues

    • using synthesised voices based on the recorded performance.

  • Record in a quiet environment using a high-quality microphone to avoid background noise.

Using Voice Acting in a Lip-sync Task

Voice acting can be applied inside a Lip-sync task as a quality-improvement option.

  1. Open the Lip-sync task.

  2. In the Script view, click the chunk you want to work on.

  3. Click the Voice acting button in the chunk toolbar.

  1. The recording interface opens

  1. Click the chunk in the Original column to hear the source voice.

    Use it as a reference for: intonation, pacing, emotion, timing.

  2. You can provide the performance in two ways:

    • Click Start recording to record directly in the interface.

    • Click Upload from PC to upload a pre-recorded audio file.

  3. After uploading or recording, preview the synthesized result and select the best take before continuing.

While recording, the following options are available:

  • Show karaoke
    Displays the text on the video at the required speed and duration.
    Words that pass the center line will no longer be audible.

  • Mute audio when recording
    Disables playback of the original audio while you record.

  • Automatically stop recording
    Stops the recording once the chunk duration ends.

  • Noise reduction
    Applies noise suppression, echo cancellation, and automatic gain control to the microphone input.
    Disable this option if you need raw, unprocessed audio.

Voice Acting task

Voice acting can also be assigned as a separate task for a voice talent.

This option is available in the dubbing pipeline after the Lip-sync stage.

Assign a Voice Acting task

To create a dedicated Voice Acting task for a voice-talent:

  1. Select Voice Acting in the pipeline after the Lip-sync stage.

  2. Assign the task to the required voice talent.

When creating the task, choose which parts of the project should be included:

  • Select all
    The performer will see all chunks in the project.

  • Select speakers
    Select one or more speakers whose lines should be recorded.

  • Open dialog
    Choose specific lines (chunks) for recording.

How the standalone task works

The Voice Acting workflow in a standalone task is identical to the one used inside a Lip-sync task.

The only difference is the assignment model:

  • the voice-talent receives a dedicated task,

  • works in a separate interface,

  • and submits the results for review.

This allows you to involve voice talents without granting access to other production stages.