Changelog

Follow new updates and improvements to Dubformer Studio.

June 2nd, 2026

Reuse AI-Generated Audio Across Chunks

A new Clone chunk action is now available in Lip-sync and Prooflistening tasks.

Reuse AI-generated result without recreating it from scratch — useful for repeated lines, flashbacks, or scenes that require identical delivery.

What’s new

  • Clone a chunk with its AI-generated result

  • Replace another chunk with the cloned version

  • Or insert the cloned chunk as a new chunk

  • Keep the same playback speed and synthesis characteristics

Read more

Bulk Audio Tags for S-tier Voices and Expressive Clones

Managing emotional delivery across multiple chunks just got faster.

Audio Tags now support bulk assignment for S-tier voices and Expressive Clones, making it easier to apply emotions, pauses, vocal styles, and sound effects at scale.

What’s new

  • Apply Audio Tags to multiple chunks at once

  • New bulk editing pop-up for faster tag assignment

  • Support for custom tags and predefined suggestions

Why it matters

Audio Tags help shape AI-generated performances with emotions, pauses, whispers, laughter, accents, and more. Bulk assignment makes it much easier to maintain consistent delivery across scenes, dialogues, reactions, or character moments.

Read more

Improve AI Pronunciation Without Changing Subtitle Text

New Set Alias support makes it possible to customize AI pronunciation while keeping subtitle text unchanged.

Use Alias when a word needs different spelling, punctuation, capitalization, or phonetic formatting to sound more natural in AI dubbing.

Why it matters

Keep subtitles clean and grammatically correct while improving pronunciation for:

  • names

  • acronyms

  • abbreviations

  • emphasized phrases

  • phonetic spellings

How it works

In a Prooflistening or Lip-sync task:

  • Select text inside a chunk

  • Click Set alias

  • Enter the spoken version for AI speech generation

The original subtitle text remains unchanged, while the alias is used for synthesis.

Read more

May 8th, 2026

New

Emotion Transfer now includes a new Performance mode.

In addition to recreating the original speaker’s voice and performance, Emotion Transfer can now recreate the original chunk’s performance with any supported voice.

Choose the voice that fits the content, character, or localization direction while keeping the original delivery — including intonation, rhythm, intensity, and duration.

Why it matters

With this update, it is possible to:

  • choose any supported voice while keeping the delivery of the original speech;

  • save several generated takes and compare them before selecting the best one;

  • fine-tune intonation, intensity, variation, and duration;

  • recreate performance chunk by chunk, in bulk, or directly to speakers.

There is no need to choose between the right voice and the right performance. The original delivery can be preserved while using a different supported voice, giving more control over casting, style, and final dubbing quality.

Availability

Performance Mode is available for S-tier, A-tier, Expressive cloned, Standard cloned, and Voice Design voices.

Supported target languages and locales: English (US), English (British), German, Spanish (Castilian), Spanish (Latin American), French (Parisian), Italian and Russian.

Learn more

For setup details and usage guidance, see the documentation

April 24th, 2026

New

Improved

Export a single TTS chunk as WAV

What’s new
Export a single TTS chunk as WAV—no full video reprocessing required.

Why it matters
Fix one chunk, export it, and continue the mix in Pro Tools without waiting.

How it works

  1. Edit the chunk.

  2. Click Generate TTS.

  3. Save progress.

  4. Open the menu next to Play TTS → Download WAV.

Full article in the Help center

Export comments from Prooflistening/Lip sync tasks

What’s new

Chunk comments can now be exported with scripts (XLSX, CSV).

Why it matters
Comments can now travel with the script—making it easy to share feedback, notes, and revision context with teams or clients outside the platform.

How it works

  1. Open a Lip-sync or Prooflistening task.

  2. Select a chunk.

  3. Leave your comments

  4. Save your progress and Process the changes

  5. Go to Downloads.

  6. Export the script (XLSX or CSV) with With comments enabled.

Full article in the Help Center

Improved User Invitations and Access Control

What’s new
User invitations have been redesigned. Add users is now Invite users, with permission-based access for Managers.

Why it matters
Admins stay in control of who can invite new users. Managers can invite Editors only when permitted, and invitation status is fully visible until accepted.

How it works

  • Admins can enable Can invite users in a Manager’s Permissions.

  • Invitations remain visible as pending until accepted, and can be resent or revoked.

Full article in the Help Center

April 14th, 2026

New

Studio now supports 15 additional source languages:

🇿🇦 Afrikaans
🇦🇲 Armenian
🇦🇿 Azerbaijani
🇧🇦 Bosnian
🇫🇮 Finnish
🇮🇸 Icelandic
🇮🇳 Kannada
🇲🇰 Macedonian
🇳🇿 Māori
🇳🇵 Nepali
🇳🇴 Norwegian
🇷🇴 Romanian
🇸🇰 Slovak
🇹🇭 Thai
🇺🇿 Uzbek

Why it matters
This expands the range of content you can bring into Studio and makes multilingual workflows more flexible.

How it works
Select any of these languages as the source language when your video is in one of them. They are also automatically detected in multilingual content when you choose Multi as the source language.

April 1st, 2026

A new Expressive voice cloning mode is now available in Dubformer Studio.

It delivers significantly more natural, emotionally rich, and high-fidelity voice output and can be controlled using emotion tags in square brackets, just like S-tier voices.

Expressive cloning also expands voice cloning support to new languages, including:
Afrikaans, Armenian, Assamese, Azerbaijani, Belarusian, Bengali, Bosnian, Catalan, Cebuano, Chichewa, Estonian, Galician, Georgian, Gujarati, Hausa, Hebrew, Icelandic, Irish, Javanese, Kannada, Kazakh, Kirghiz, Latvian, Lingala, Lithuanian, Luxembourgish, Macedonian, Malayalam, Marathi, Nepali, Pashto, Persian, Punjabi, Serbian, Sindhi, Slovenian, Somali, Swahili, Telugu, Thai, Urdu, Welsh.

The previous cloning mode remains available and is now called Standard.

Why it matters

  • Create more realistic and expressive voiceovers with emotional control

  • Use cloning in many more languages, including previously unsupported ones

  • Choose between quality (Expressive) and scalability (Standard) depending on your workflow

How it works

  • Select Expressive or Standard cloning during project setup or in the Speakers tab

  • Use emotion tags (e.g. [laughs], [whispers]) with Expressive mode

  • Switch modes at any time depending on your needs

Learn more in the documentation:
https://help.dubformer.ai/en/help/articles/4964903-voice-cloning

March 5th, 2026

New

Jump to time

What’s new

A new Jump to time option is now available in the editor, allowing quick navigation to a specific timestamp.

Why it matters
This makes it easier to locate and review specific moments in long scripts without manual scrolling.

How it works

  1. Open Jump to time in the interface.

  2. Enter a timestamp in the format 00:00:00.000.

  3. Choose whether to navigate using Original or Translation chunks.

  4. Click Jump to move directly to the corresponding chunk.

Learn more in the documentation.

Generate AAF Only

What’s new
A new Generate AAF Only option is now available in Lip-sync and Prooflistening tasks. It allows exporting an AAF file without reprocessing the entire video.

Why it matters
When final mixing is done outside Dubformer Studio, regenerating the full video is unnecessary. Generating AAF only is typically 2–3× faster than running the full Process changes pipeline.

How it works

  1. Open a Lip-sync or Prooflistening task.

  2. Click the arrow next to Process changes.

  3. Select Generate AAF Only.

  4. Download the generated file as usual.

Learn more in the documentation.

February 10th, 2026

New

Pivot language

What’s new

A new Pivot Language option is now available for projects, allowing content to be processed through an intermediate language before reaching the final targets.

Why it matters

This improves quality for multilingual source content and rare language pairs, and helps standardize scripts across multi-language workflows.

How it works

  • Enable Pivot language during project setup.

  • Select the intermediate language.

  • Subsequent tasks use the pivot language as the source.

Learn more in the documentation.

Localised Cast export

What’s new

You can now download the localised cast after a dubbing version is generated in Lip-sync or Prooflistening tasks in both CSV and XLSX formats.

Why it matters

This makes it easier to review which characters were voiced by which AI voices, share cast lists with production teams, and keep records clean for reporting or QA.

How it works

  1. Open a Lip-sync or Prooflistening task with a generated version.

  2. Click Download.

  3. In the file list menu, select Preview and Download.

  4. Choose CSV or XLSX.

Learn more in the documentation.

January 26th, 2026

New

Improved

🟣🎙️ 42 New Languages Now Supported with S-tier Voices

Dubformer Studio has added S-tier voices for 42 new languages — many of which previously had limited or no voice support in the platform.

Why it matters
S-tier voices deliver significantly improved naturalness, expressiveness, and audio fidelity — helping you create more realistic, engaging voiceovers across a much broader language set.

How it works

When selecting voices in the Studio, S-tier options will now appear for the newly supported languages.

Learn more in our Help Centre.

New languages available with S-tier voices

Afrikaans, Armenian, Assamese, Azerbaijani, Belarusian, Bengali, Bosnian, Catalan, Cebuano, Chichewa, Estonian, Galician, Georgian, Gujarati, Hausa, Hebrew, Icelandic, Irish, Javanese, Kannada, Kazakh, Kirghiz, Latvian, Lingala, Lithuanian, Luxembourgish, Macedonian, Malayalam, Marathi, Nepali, Pashto, Persian, Punjabi, Serbian, Sindhi, Slovenian, Somali, Swahili, Telugu, Thai, Urdu, Welsh

🟣 📊 Script Export Now Available in XLSX and CSV

What’s new

You can now export scripts from Dubformer Studio in XLSX and CSV formats.

Why it matters

These formats make it easier to review, edit, and share scripts in spreadsheets — whether you’re preparing QC, running batch edits, or collaborating with external teams.

How it works

Open the export menu and select XLSX or CSV to download your script in a spreadsheet-friendly format.

🟣🛡️ “Moderated Voice” Label Added

What’s new

Some Special voices using real-time moderation are now labeled as “Moderated voice” in the Studio.

Why it matters

Plan projects more confidently and avoid unexpected blocked chunks — especially in sensitive or regulated use cases.

How it works

When browsing or selecting voices, moderated voices are now clearly marked in the UI, with links to detailed documentation.

🟣 “Last Seen” Sorting Added to Users Table

What’s new

You can now sort the Users table by Last seen to quickly see who was active most recently.

Why it matters

Spot active and inactive users at a glance and keep account usage under control.

How it works

Open the Users tab and sort by the Last seen column to organize users by recent activity.

🟣 🌍 New Target Languages Added

What’s new

Five new target languages are now supported in Dubformer Studio.

Why it matters

Reach new audiences and expand your localization workflows with accurate language support.

How it works

You can select these languages as target languages in your projects.
The full and growing list is available in our Help Centre.

Newly added target languages

  • Assamese (as-IN)

  • Hausa (ha-NG)

  • Lingala (ln-CD)

  • Chichewa (ny-MW)

  • Sindhi (sd-PK)