8. AI enabled - Recent Threads

How do Chinese Translators Make Use of AI in Trados Studio?

Jay Chen — Wed, 25 Feb 2026 02:54:59 GMT

Please correct me if I were wrong, but as far as I know, Trados Studio 2024 currently only supports OpenAI and Azure OpenAI, neither of which is available to Chinese users.

So, as a Chinese translator, how do I, or my team in China, make use of AI in Trados Studio?

Is there any chance Trados Studio extends the coverage of the current OpenAI Translation Provider plugin to other major AI providers, like, QWEN, DeepSeek, Claude, Gemini, or even custom models? Or develop such a plugin based on the existing one? The need for custom models would be extremely useful for companies or teams with their own AI infrastructure and model resources and prefer not to share their contents with any other LLM providers like the ones mentioned above.

Thanks.

MISTRAL AI

PASCALE HOUBEN — Sat, 10 May 2025 06:10:41 GMT

Can I use my MISTRAL API code to work with Trados Studio?

Where can I insert it?

Thank you

Machine translation provider and confidentiality

Rodanthe Papadiou — Mon, 05 May 2025 11:18:32 GMT

Dear colleagues, I would like to ask a recommendation for a machine translation provider for Trados 2024.

Which Machine Translation provider would you recommend for data confidentiality? I am thinking of proceeding with an OpenAI subscription but what about confidentiality?

Many thanks in advance

Rodanthi

Is AI assistant available with Trados 2024 Freelance

Sonia Gouin — Tue, 11 Mar 2025 18:35:58 GMT

Hi, after attending a seminar on the new functionalities of Trados 2024, I was told that Trados Copilot was only available on the professional versions of Trados i.e. Teams, Accelerate or Enterprise. Now, I'm interested in using the AI assistant features and looking into getting an Azure membership. Will this feature be compatible with Trados Freelance 2024 or do I need to upgrade? Thanks in advance.

How to Select a Specific OpenAI Assistant in Trados AI Assistant? Default Assistant Always Used

Peter Oehmen — Wed, 12 Feb 2025 08:15:20 GMT

Hi everyone,

I would be happy if someone could help me and point me into the right direction. Maybe I am trying something that simply isn't possible with Studio.
So, what I am trying to achieve:

I am using Trados Studio 2024 with the integrated AI Assistant to improve translations and text quality via the OpenAI API. I have set up multiple Assistants on the OpenAI platform, each tailored to my specific needs.

My Goal:
I want Trados Studio to call a specific OpenAI Assistant, rather than always using the default Assistant.

My Current Configuration:
Provider: OpenAI
Endpoint: api.openai.com/.../completions
Model: gpt-4-turbo
API Key: My personal OpenAI API key
Completion Type: Chat Completion
However, there is no option in Trados Studio AI Assistant settings to specify an assistant_id. As a result, every request defaults to OpenAI’s standard Assistant instead of my custom-trained Assistant.

What I Have Tried So Far:
Changed the API endpoint to api.openai.com/.../threads → Trados throws a connection error.
Created a dedicated API key for my desired Assistant → Trados still defaults to the standard Assistant.
Tried a system prompt workaround → didn't work.
My Question:
Is there a way to select a specific OpenAI Assistant in Trados Studio 2024, instead of always using the default one?
If not directly, is there a workaround, or could this be achieved through a script or plugin?

Looking forward to your insights and solutions!

Thanks in advance!

XML tags causing issues with machine translation results

David McDermit — Tue, 11 Feb 2025 13:49:29 GMT

Hello

Talked with out Swedish translator and seems the SW Deepl engine is giving some odd answers.

In Segment 3 there is a mix, what linguist said, is maybe Norwegian or Finnish in the sentence. You will also see the word varlden repeated. That is World”. Linguist also stated that segment 4 is not accurate at all.

Did reach out to our machine translation provider to see if it was with the MT engine.

This is what they told me: "The segments are heavily tagged, which leads to the difficulties you've encountered.

When files are processed by systems using tags, such as Trados or similar CAT tools, text can be wrapped in XML tags. This wrapping might happen due to incorrect document structure recognition, encoding or markup errors during import/export processes, or usage of XML-style data storage formats which are particularly seen when converting file types, like from Word to PDF."

What would be causing this and how to fix it?

Oh, using Trados SR2 17.2.11.19134 and Windows 11 Enterprise

Find-and-replace all in target text, how to do it?

Andrew Levine — Fri, 08 Nov 2024 20:57:05 GMT

Hello,

After visiting the Trados booth at the ATA conference this year, I was sold on the AI features of Studio 2024. I now have got AI Assistant working in Studio 2024. At the booth, I was told that I could create prompts that would find-and-replace target text based on instructions, e.g. "Wherever the subscripts in the target text for chemical formulas don't match the source text placement, change the subscripts in the TT to match the ST." However I cannot figure out how to do this. Even simpler queries like "Ensure that the verbs 'comprendre' and 'comporter' are always translated by the grammatically appropriate form of 'comprise'" seems beyond my reach. Can anyone help me out with figuring out how to run these prompts on the text? Thanks!

Regards,

Andrew

AI Assistant not working

Emi Amber — Sat, 28 Sep 2024 12:03:01 GMT

Hi,

I have just startet using AI assistant (OpenAI gpt-4o model) and it is not working as it should. F. eks. in the example below it should automatically sett "lege" in stead of "dr." because this is how this term is translated in the Termbase "lek.med = lege". AI assistant is enabled with Refine translation prompt. Should it not have insertet "lege" automatically? Or have i misunderstood something?

Please, look at the printscreens below.

AI assistant is not showing that anything is wrong with the sentence, though the word dr. is an incorrect translation of lek.med and "Refine Translation" prompt is on.

lek.med exists in the activ Termbase, see: Term recognition in the first pic.

My settings are as follows: Is there anything wrong in the settings? or should I do something more than just to tick the right boxes?

Can anyone help to do this the right way?

Or paste a link to the documentation that shows the right way to do it? Thank you in advance.!

Plugin installer error

Jeanny Jang — Fri, 27 Sep 2024 03:41:40 GMT

I tried to install 2 plugins, BUT I failed due to below message.

Could you let me know why I can't install.

New OpenAI o1 model

Daniel Hug — Wed, 18 Sep 2024 08:22:37 GMT

For German readers, the FAZ has an interesting article about the new OpenAI o1 LLM. Especially interesting as it is not a "newer, more expensive, better" model (emphases are mine):

o1 is in many ways a significant break with the LLM trend described above. Inference takes longer with o1. So the model feels slower. Much slower. Open AI humanises the longer computing time with "thinking". But why is o1 a break? Firstly, the model is not optimised for regular, run-of-the-mill requests such as "rephrase this email in a more professional tone". The now longer and more expensive "thinking time" compared to other models gives o1 new capabilities. It is better at logical tasks, such as maths or programming, than any other model. At the same time, it is no better, and often worse, at text formulation than classic LLMs such as Claude or GPT-4o.

For the first time, o1 is an LLM that can perform complex tasks better than simple tasks, even if the user accidentally puts the tasks in the same area. If you give o1 a simple task, Open AI warns, the model may 'think' too much about the solution and complicate the result. The LLM landscape as a whole is not intuitive, and with o1 this is exacerbated.

For us as Trados Studio users, this might mean we can be quite relaxed about not having an integration to this new model right away - OpenAI might introduce a move language-oriented variety of this LLM at a later point, just as GPT-3 and GPT-4 grew into families of LLMs with different abilities (and costs).

My personal opinion is that currently the real productivity boosts for translation processes are less in more powerful models, but in comprehensive application of the existing models (not even the most advanced ones) to reduce the "donkey-work" and highlight the areas where human translation and editing skills are most needed.

How to get started with AI in Trados

Marie Brotnov — Tue, 10 Sep 2024 19:27:21 GMT

I'm trying to wrap my brain around this but I'm getting conflicting information it seems. Do I just install the free Language Weaver and/or OpenAI apps? Because one webinar said you have to buy Trados Enterprise or Accelerate to be able to use AI in your workflow. Also, are my data secure or not? The same webinar first said no it's not secure, then later it said yes the data are secure and are not shared. Clearly I'm missing something.

How are reused the data collected by Trados CoPilot?

Cédric Deplanque — Sat, 17 Aug 2024 19:00:45 GMT

Hello everyone,

Here the more detailed version of my question:

Does the data collected by Trados CoPilot's LLMs (GPT-3.5 and GPT-4) when working with it on a project are stored on a dedicated server linked to our RWS account ?
Or are they sent to OpenAI servers to train their LLMs ?

I ask this because I attended the webinar on June 25th about Trados Studio 2024 and its new features, and at some point someone asked: "How does the use of A.I. affect confidentiality issues?"

To this question, Daniel Brockmann answered we should ask our customers if they're okay with us using A.I. to be more productive, like in any typical translation contract's part about confidential content. If the customers are not okay, we just have to disable the option. Up to us to decide in cases with no real confidential matters from what I understood.

But he didn't specify if it could be a problem in the sense that the data collected by Trados CoPilot could reappear in its future suggestions on other projects (or just be stored somewhere less protected against hack, like our PC), or if it could be a problem in the sense that the data collected could be used by OpenAI to train its LLMs.

So : is Trados CoPilot directly connected to OpenAI servers?

I really need to know.

Thanks in advance for your help.

Best regards,
Céd'.

AI – the opportunity of a lifetime?

Daniel Hug — Wed, 26 Jun 2024 07:45:38 GMT

I just read the D:ECONOMY newsletter of the Frankfurter Allgemeine Zeitung, where Holger Schmidt states:

“Whether a country capitalises on this opportunity of the century depends crucially on individual commitment. One and a half years after the launch of ChatGPT, there are already considerable differences in the world: low-income, non-Western countries such as China and India have recognised the opportunity and are achieving the highest usage rates. People in developed countries such as Switzerland, Australia and Singapore, which are at the top of economic digitalisation rankings, also use the technology regularly. The USA is in the midfield, while most European countries – including Germany – are relatively far behind in the usage statistics.”

I was sufficiently intrigued to visit Trados Studio's “AI enabled” forum and found that the last entry is from four months ago. Are we seizing the opportunity, or are we trying to hold out “like children in sand castles when the tide comes in” (Gandalf, I think).

For Studio users, who are predominantly not programmers, which chances are there to integrate AI into our workflows? Which tools would we need to do this?

The last great technology was the World Wide Web, according to Holger Schmidt. If we take the German retail industry, it totally re-shaped the landscape. The giants of old are gone: Karstadt, Hertie, Neckermann, Quelle etc. Some survived, because they harnessed the new technology. Otto comes to mind.

Both users and providers of software are caught up in this whirlwind of change, and while there might still be some who translate venerable texts using fountain pens and paper notepads, the industry will change and has changed to some degree already.

How can we as the users communicate to RWS what we believe Trados Studio, a software we know well and trust in, needs to stay on top of this change. How can RWS meet the need? Yes, there is the AI assistant, but it is still in its infancy and rather limited in many ways. Maybe a renewed push to enable users to write their own apps (or apps for the AppStore) is what the time calls for? Programming languages have changed dramatically, and programming itself has become more accessible with AI, too. Video tutorials to guide us along the first steps to the first visible results? Or maybe it's something else. If software development is like paddling down a river, we've come to rapids and waterfalls now, and we might have to change the way we go about things.

Detailed user feedback is valuable for companies – feedback that goes beyond complaints that the product is not like what I saw in Star Trek the other day. Let this forum be the place where we give feedback of use cases that are both realistic and real, like this one. There is a joint interest or RWS and Trados Studio users here. My hope is for this forum to reflect this.

Daniel

Post-editing with AI

Almudena Ballester — Mon, 26 Feb 2024 11:39:44 GMT

Hi Community,

I wonder if there is a way to instruct GPT within Trados to post-edit the target translations, already translated with NMT (another provider). I am aware that you can perform this task segment by segment, using different prompts, like "Refine translations", which changes (but not always, which is annoying) the translated segment according to the project terms from the Multiterm.

But I am looking for a way to do it for the whole project at once. In batch tasks, I see the option "Pre-translate Files with AI Professional", but I don't want to resend to a NMT engine what is already pre-translated. I just need to post-edit the destination.

Is this option possible somehow?

Best regards,

Almudena

Revise all segments of a text in Trados using gpt4

Letizia Clerici — Wed, 15 Nov 2023 09:30:58 GMT

How to ask Trados to revise all the segments of a project - pretranslated with Deepl - using the GPT4 API without having to confirm each segment? The chatgpt4 api is already running.

Search & Replace for multiple terms/phrases

Paul — Fri, 28 Jul 2023 07:31:40 GMT

Hi,

I'm just responding to this thread in here with a possible AHK solution:

RE: Search & replace multiple words/terms in pre-translated segments?

^!h:: ; The hotkey for Ctrl+Alt+H to start the process
global filePaths := {} ; Create an associative array to store full file paths
global fileNames := "" ; Create a variable to store the file names
global PosX, PosY ; Create global variables to store the dropdown menu's position

Gui, Add, DropDownList, w450 vFilePath ; Add a dropdown list to the GUI with width of 400
Gui, Font, s12 ; Set the font size to 12

Loop, Read, c:\Users\pfilkin\Documents\SDL\AppStore\2023\Search_Replace_AHK\settings.txt ; Read the hardcoded settings file line by line
{
    SplitPath, A_LoopReadLine, name, dir, ext, name_no_ext, drive ; Split the file path into parts
    fileNames .= name_no_ext . "|" ; Add the file name (without extension) to the string, separated by "|"
    filePaths[name_no_ext] := A_LoopReadLine ; Store the full file path in the associative array
}

fileNames := SubStr(fileNames, 1, StrLen(fileNames) - 1) ; Remove the last "|"
GuiControl,, FilePath, %fileNames% ; Set the items of the dropdown list

WinGetPos, PosX, PosY,,, A ; Get the position of the active window
PosY := PosY - 150 ; Subtract 150 from PosY
Gui, Show, x%PosX% y%PosY% w500 h100, Select a file ; Show the GUI at the position of the active window with a larger window
WinSet, AlwaysOnTop, On, A ; Make the GUI always stay on top of other windows
return

GuiClose: ; When the GUI is closed
Gui, Submit, NoHide ; Store the dropdown list's current selection in the variable filePath
filePath := filePaths[filePath] ; Retrieve the full file path from the associative array
Gui, Destroy ; Destroy the GUI
GoSub, StartReplace ; Continue with the search and replace operation
return

StartReplace:
WinActivate, ahk_exe SDLTradosStudio.exe ; Activate SDL Trados Studio

Loop, Read, %filePath% ; Read the selected file line by line
{
    StringSplit, line, A_LoopReadLine, `t ; Split the line into "line1" (search term) and "line2" (target term)
    searchTerm := line1 ; Assign the search term
    targetTerm := line2 ; Assign the target term

    ; Click in the "Find what" field
    ControlClick, Edit2, ahk_exe SDLTradosStudio.exe
    Sleep, 100
    ; Select all text and delete it
    Send, {Home}+{End}{Del}
    Sleep, 100
    ; Send the search term keystrokes
    Send, {Text}%searchTerm%
    Sleep, 100

    ; Click in the "Replace with" field
    ControlClick, Edit1, ahk_exe SDLTradosStudio.exe
    Sleep, 100
    ; Select all text and delete it
    Send, {Home}+{End}{Del}
    Sleep, 100
    ; Send the target term keystrokes
    Send, {Text}%targetTerm%
    Sleep, 100

    ; Click the "Replace All" button
    ControlClick, WindowsForms10.BUTTON.app.0.ea119_r8_ad19, ahk_exe SDLTradosStudio.exe
    Sleep, 100
}

; PosY := PosY - 150 ; Subtract 150 from PosY
Gui, 2:New, +AlwaysOnTop ; Create a new GUI for our custom message box
Gui, 2:Font, s12 ; Set the font size to 12
Gui, 2:Add, Text, w500 h50, The search and replace operation is complete. ; Add a text element to the GUI
Gui, 2:Show, x%PosX% y%PosY% w500 h100, Operation Complete ; Show the GUI at the position of the dropdown menu with the title "Operation Complete"

Sleep, 500 ; Wait for 500 milliseconds (half a second)
WinActivate, Operation Complete ; Activate the GUI window using its unique title

return

2GuiClose: ; When the custom message box is closed
Gui, 2:Destroy ; Destroy the GUI
return

I definitely didn't write this on my own... I used ChatGPT by starting small and slowly enhancing the script until I had what I needed. I think it took me around 3-hours from start to finish last night, but I think it's a good example of how we can use AI to help with our work. I created a short video to explain how this works as it may not be obvious without some context.

community.rws.com/.../0474.037_5F00_Video_5F00_2023_2D00_07_2D00_28.mp4

Calculate TUs in SDLTM

Giannis Ouzounis — Thu, 06 Apr 2023 15:07:39 GMT

Dear all,

Is there any way (with any Trados function, plugin, or third party) to calculate the TUs included in an SDLTM without converting into TMX?

Thanks!

Giannis

"This project cannot be opened in the Studio Edition you ar using"

Anette Schütt Christensen — Wed, 29 Mar 2023 11:05:45 GMT

I am working on a project and all of a sudden after closing it down I can't reopen it, and it has disappeared from my project list. The error message is "This project cannot be opened in the Studio Edition you are using. Only project packages or single documents can be opened." Can anyone please help? I have already tried to save the project locally on my computer instead of its usual location on One Drive but no luck.

Thank you!

chat GPT4

Sreekanth V — Thu, 23 Mar 2023 10:53:33 GMT

Hello Team

please let me know by when chat GPT MT plugins available in RWS live teams

Regards

Sreekanth

Removal of unnecessary hard returns.

Paul — Fri, 17 Mar 2023 09:50:59 GMT

This is really a reply to this thread: RE: Solving mid-sentence line breaks in PowerPoint ... James Plastow

I used a chrome extension ( https://chrome.google.com/webstore/detail/chatgpt-sidebar-support-g/difoiogjjojoaoomphldepapgpbgkhkb ) to work online in Office 365 and use AI to remove the hard breaks from text boxes in Powerpoint. I am absolutely certain that a developer could make use of this and provide a neater solution that could process a complete file, but this test is just interesting to see what's possible when we think about the uses for AI in our business.

I also appreciate that confidentiality is an issue, but if you can use a tool like this for your content then perhaps it's a useful idea to resolve you problem. I recorded a short video as I played with it so it's a bit rough, but perhaps helpful:

community.rws.com/.../hardreturns_5F00_005_5F00_Video_5F00_2023_2D00_03_2D00_17.mp4

Thesaurus for Trados Studio

Mark Lewis — Wed, 01 Mar 2023 12:28:01 GMT

Hello.

I've been looking for a good thesaurus integrated into studio.

I found Sketch Engine which seems good but a little expensive at €19 for a freelancer account.

Are there any other tools which similarly integrate a thesaurus but cost less?

Thanks..

ChatGPT to learn and create regex expressions

Jesús Prieto — Tue, 28 Feb 2023 08:28:32 GMT

I’ve just tested ChatGPT to create a regex expression and it worked!

I asked ChatGPT: Whats the regex to match a string without the string hello?

And the answer was:

^(?!.*hello).*$

with a helpful explanation:

Always take the answers from ChatGPT with a grain of salt, because they can be plain wrong, but I believe this tool can be a real helper to create regular expressions or AutoHotkey macros.

The beginnings of practical applications for AI

Paul — Thu, 09 Feb 2023 16:50:51 GMT

I thought I'd kick this off with why we created this forum. It's probably obvious, but I imagine everyone has been exposed to information in the news, or even dabbled with it themselves, on ChatGPT. In case not then here's how ChatGPT describes itself:

ChatGPT is a conversational AI language model developed by OpenAI. It's a variant of the GPT (Generative Pretrained Transformer) architecture, specifically designed to generate human-like text based on the input it receives. It has been trained on a massive corpus of text data and is capable of performing a variety of language tasks such as answering questions, generating text, and carrying out conversations that are coherent and contextually appropriate. ChatGPT can be used in a variety of applications, including customer service, virtual assistants, and chatbots.

This definitely underestimates it's uses, and as I've been playing with a little over the last weeks, and as we have been even building proof of concepts we could implement to support our users better, I keep finding some great ways to use it in my day to day life.

I started with a couple of articles I published on my blog. The latest one here:

https://multifarious.filkin.com/2023/02/04/say-goodbye-to-doppelgangers-with-chatgpt/

Followed up by an update to the previous one here:

https://multifarious.filkin.com/2023/01/29/tm-corruption/

But even this is scratching the surface. I'm also not the only one who is probably using it, nor am I the one with the best ideas! So I thought we could use this platform to look at the opportunities together. If we see any popping up in the other forums in this group we'll move them into here so we have a single source of useful ideas and tips and tricks around using this sort of technology to help us with our work using Trados toolsets.

I'm looking forward to what comes up!

Trados 2021 > Filters for exporting translation memories

Almudena Ballester — Thu, 09 Feb 2023 15:17:50 GMT

Dear community:

Why is it that, while we can create filters for searching in translation memories, save them, and use the same for batch delete, there is no way to use those saved filters for exporting?

There is no option to import filters in export options:

Once and again I need to export tmxs fulfilling a mixed bunch of conditions (project number + a range of dates, etc.). But I cannot reuse these conditions from a file, I must write them each time by adding them one by one. This is quite frustrating, especially when the filters are complex and several conditions come together, or when there are many conditions. Is it ever going to be implemented?

Thanks in advance,

Almudena

Extract TM source files list

Liza Thetiot — Thu, 09 Feb 2023 14:27:41 GMT

Hi everyone,

I'd like to update some (massive) TMs, but I don't know which source files have already been aligned and added, so that's the first item on my to-do list before adding any new alignment result.

So far the only way I've found is to simply open the TM in Trados, look at the third column and copy/paste the source file name somewhere.

Is there any automated way to get the list of all the source files in my TM? I've thought about SQL-ing this, but I don't know enough about it.

Any help would be greatly appreciated! Thanks!