Translation, Pronunciation and Voice glossaries, TTS-presets

Assets

Use a Voices Glossary to define which voices are used for specific speakers across one or multiple projects.
This ensures consistent voice assignment throughout the pipeline.

Voices Glossary

A pronunciation glossary helps AI voices pronounce specific terms consistently across a project. Use it for character and place names, brand names, acronyms, technical terms, or other words that may require a specific pronunciation. Instead of correcting the same term during every proofreading pass, add it to the glossary once and reuse it across languages and voices.

Pronunciation Glossary (save and reuse alias)

Use a Translation Glossary across multiple projects. Applying a translation glossary to your workflow ensures consistency and efficiency throughout the pipeline.

Translation Glossary

Changelog

Dubformer Studio

Getting started

Learn how to invite a new team member to your workspace. 

Invite Team Members

This video gives a high-level overview of how projects work in Dubformer Studio.
You will learn how content moves through the pipeline — from transcription and translation to voice synthesis, editing, and final export.

Project Workflow: From Transcription to Final Video

This video focuses on the prooflistening stage in Dubformer Studio and shows practical techniques to refine AI-generated voiceovers. You’ll learn how to improve clarity, pacing, intonation, and overall performance — with real tips and hacks tailored for fitness content.

Perfecting AI Voiceovers: Prooflistening Tips for Fitness Content (video guide)

This guide focuses on prooflistening for AI-dubbed live-action content such as dramas, TV series, and films.
You will learn practical techniques to refine performance, improve emotional consistency, adjust timing and pacing, and achieve more natural, actor-driven results when working with AI voices.

AI Dubbing for Drama: Prooflistening Techniques

This document provides an overview of the languages that are currently supported as source and target languages. 

Supported Source and Target Languages

Voice samples let you audition synthetic voices before you commit to them in production. You pick voices from the library, give them a line to read, and get a ZIP archive of WAV files — one file per voice — that you can share with a director, client, or casting team for approval.

Voice samples for external casting


Emotion Transfer for Dubbing

What is Emotion transfer?

Creating voices with Emotion transfer

Emotion Transfer: perfomance mode

Emotion Transfer often produces high-quality results out of the box.
For additional control and refinement, the following editing methods help you fine-tune performance, timing, and expression.

Emotion Transfer: Best Practices

Library voices, Voice cloning, Voice acting, Voice design, Audio tags

Voices & AI Dubbing Enhancement Toolkit

Learn how to create a new voice clone directly while working on a project if the default voice does not meet your quality or performance expectations.

Create a New Voice Clone During Prooflistening

Use voice cloning to create a reusable voice based on an audio recording.
This is useful for retakes, voice continuity, or creating variations of the same voice with different tone or emotion.

Create a Cloned Voice from an Audio Sample

This article explains how original voice removal works when Auto Mixing is enabled in dubbing projects, and how timing boundaries and crossfade settings affect the final result.

Original Voice Removal in Auto Mixing

Library voices

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

Voice Design lets you generate a synthetic voice based on a written description — no recording required.

Voice Design

A guide on how to craft voices from a text prompt.

Voice Design Prompting

Voice Cloning

Audio Tags (prompts in [brackets]) in S-tier Voices and Expressive Clones

Task Editor: Tools and Controls

Change speaker for selected chunks

Delete one or several chunks

Apply an emotion to selected chunks

Chunk Comments

Improve pronunciation without changing subtitle text (Set alias)

Reuse AI-Generated Audio Across Chunks

The TTS preset option lets you save voiced chunks and reuse them within a single video or across multiple videos.

Reuse chunks across projects (TTS preset)

Bring a finished voice recording into your project as a track and use it as voice guidance for AI voices in Voice acting. This option lets you import them into the studio as one AAF file instead of uploading clips line by line

Import voice recordings for voice acting (AAF)

How to organise projects in the Workspace

Folders, Projects, Tasks

Group related projects into folders to keep your workspace organized and easier to navigate.

Folders, Projects and Statuses

Use this page to upload source media and set up all basic project parameters.

Create a New Project 


This guide explains two methods for preserving original voice (OV) in selected parts of your media while dubbing the rest. Whether you mark segments as non-voiced during transcription or upload/edit a transcription that already excludes those segments, the system ensures that these parts remain untouched by synthesized voices throughout translation, lip-sync, and export.

How to Preserve Original Voice in Selected Segments through dubbing stages


Use the Download button to preview and download all files generated during your project workflow.

File Exports from Dubformer Studio

Use this flow to assign a project task to an editor and ensure the task is ready to start.

Assign a Task to an Editor 

You can assign editors to all project stages in advance during project creation.
This helps plan workloads ahead of time and ensures a smooth handover between stages.

Pre-assign Editors Across the Project Pipeline

Use this workflow to replace the editor assigned to a task or to continue work with another editor while preserving or discarding previous changes.

Changing the Assignee for a Task

Use this option to permanently remove a project and all related materials from Dubformer Studio.

Delete a Project


Use this action to permanently remove a video from a project.

Delete a Video from a Project

Uploading Custom Scripts 

Pivot language is an intermediate step in the localization workflow, allowing content to be processed through a selected language before being delivered in the final target language.

Pivot (Intermediate) Language

Clone a media project setup

Automated Voice Selection with Voice Labels

Auto-mixing

Dubbing, Audio description, Voice lines, Subtitling, Transcribing, Translation

Workflows

This guide explains how to create a dubbing project in Dubformer Studio and move it through all production stages — from media upload to final delivery.

Dubbing Workflow: Creating and Completing a Project in Studio

This guide covers the full Audio Description (AD) workflow in Dubformer Studio: creating the project, reviewing the automatically generated script, selecting narration voices, and refining text and performance before delivery.

Audio Description 

Voice Lines is designed for voice-over projects that work with individual lines rather than video and a timeline. Upload an .xlsx file with target-language lines, generate the voice-over, and review each line in the editor. A script can contain a single line or a batch of lines. 
Reference WAV files can also be uploaded as an archive when the original recordings should be used as a reference for generation.



Voice Lines

Subtitling in Dubformer Studio

2-FA, Roles, Access, Authorization, Billing

Workspace and User management

Authentication Restrictions configuration

Use roles in Dubformer Studio to manage access levels and define what each user can do inside your company workspace. Below you can find a description of all available roles.

Roles and Workspaces


Use access controls to protect cloned voices created for specific projects and prevent them from being used unintentionally in other projects.

Managing Access to Cloned Voices

Dubformer Studio uses a credit-based billing model.
Credits are consumed when you process media using available workflows.