Contact Me
If you have any questions, comments or suggestions please fee free to share your feedback by filling the form below in Feedback & Comments section.
Note: By default all of your comments and feedback are made public and visible on this page. If you want to share something in private, you can email me at gakbar {at} gmail {.} com, or you can mention this in your comments text.
Hi Akbar, if you have time would you consider to put Grok 4 Fast as translation model? Or you have your own reasons to not to do that?
Hi Andi, thanks for bringing this to my attention. I have now enabled the Grok 4 Fast model in the xAI translator.
Regards, Akbar
Akbar, any progress on what we discussed regarding my #2 suggestion which you said you would work on?
Thank you
Hi Alexis,
Thanks for reminding and sorry I forgot to update this, but this tweak was also released with some other fixes with 9th Aug update. Please let me know if you still run into problem with this or it’s not working as expected.
Regards, Akbar
Hi! First of all, great tool you made here with the Subtitle Translator & Editor 😉
I’d have maybe 2 suggestions, if it’s possible. I guess you add one main prompt for every LLM, so if it’s the case:
– add a line like “translate local idioms to the targeted language accordingly if possible, or remove it when possible”.
– add the option to select a tone: formal or informal.
Thanks again for your work!
Hi Nicodemus, thanks for your feedback and suggestion. Though there are slightly different instructions, but the overall prompt for every LLM is same as you hinted.
For any customisation or prompt extensions, this is somewhat already support. You can do this by:
1. Click on the grear/settings icon next to LLM model dropdown.
2. This should show toggle an additional area with more configuration per LLM model.
3. Click on the pencil icon next to “Prompt Extension”
4. This should open a new dialog where you can add any additional instructions, as you hinted above, in the “Additional instructions or hits” text area.
This works for nearly all the LLM based translators. I hope this helps. If run into any issues or have further questions, please let me know.
Regards, Akbar
Oh! Sorry I looked for it but not enough it seems ^^
Thanks!
Hey, me again. Sorry but I can’t see the “Prompt Extension” area you mention ^^’ I tried with 2 browsers, including Firefox.
Okay, no worries. I have added this to the help section for future users too:
https://blog.syedgakbar.com/subtitles-translator-help-tips/#llm-prompt-extension
Please let me know if still run into any issues.
Regards, Akbar
OK now I see why I couldn’t find it: I use DeepL, and the wheel doesn’t show up with this model ^^
Thanks again 😉
Great tool, now there are two small enhancements which would make it even better:
1. Would be it possible to support more than 20 srt files? Maybe 40 or 50 please
2. When you input an srt file like xyz.en.srt, you make a translation to French, you save it, the current output file is xyz.en.fr.srt, which is not good since it should be xyz.fr.srt, right? Could you make this change so that it can take any xyz.language.srt and ouput xyz.translation_language.srt.
Thank you so much
Thanks for the feedback and suggestions. Regarding your suggestions:
> Would be it possible to support more than 20 srt files? Maybe 40 or 50 please
Sure, if you just login as Google user before uploading files, this limit is automatically increased to 100.
> Could you make this change so that it can take any xyz.language.srt and ouput xyz.translation_language.srt.
I think this is quite reasonable suggestion. I will try to look into this pretty soon.
Regards, Akbar
OK thank you, this would be very helpful
Please send me a notice when I can try it
Sure, the increased upload limit with login should already be working. I will work on the fix to tweak the file extension in week or so.
Regards, Akbar
Yes a limit of 100 is perfect and working
Is it possible for multiple google accounts to be linked to the one “Projects” and “Balance” ?
Or, can I load money into an account that I am not logged into on your website?
ie I would like several people to be able to use this website, but I want to handle the payments.
And ideally I’d like to be able to share their projects.
Thanks for reaching out and sharing this query Paul. An interesting scenario, and I can definitely see the business value to manage payments from a central account. I think a proper implementation would be to introduce a concept of Teams or Business account to manage sub-accounts balances centrally. But it’s slightly bigger project to implement. I can think of two suggestions/workarounds for now:
1) You can create separate Google account for your business and load money into it. You can then share this Google account with your team members. I can see how it would be then tricky to track/audit i.e.g who did the translation? For this, may be they can name their Subtitles file to identity project, or I can quite easily add another helper field in order like Project Name to help you identify this from the invoices.
2) Other option could be that you can top-up money to central account and then email me the split you want to the distribute between various accounts, and I can do that for you. It’s a bit manual process, and might not be all what you are looking for. But might get you going the meantime.
What do you think?
Regards,
Akbar
ya estoy teniendo muchos problemas a la hora de traducir, cuando me da los resultados hay demasiados espacios en blancos que no lo traduce…
Hi Patrick, the missing or misaligned translation is unfortunately is still a problem in some translator models. You can read more about the reason and some possible workarounds here:
https://blog.syedgakbar.com/subtitles-translator-faq/#misaligned-translation
I have initiated full refund for these translations with partial results.
Regards, Akbar
Hi there just paid with Ideal but no translation. help please
Hi Caspar,
I see few successful translations against your user. It it that you can’t access these translated file or some of the translation failed or contains missing rows?
FYI, you can access all your past translation from the following page (after sign-in):
https://www.syedgakbar.com/projects/user-subtitles
Regards,
Akbar
hi I made a translation and was incomplete. order QfVMmOAXXXXX.
Sorry for the trouble. I will investigate further on what went wrong there. But I have issued full refund for now.
Regards, Akbar
Hello, I can’t pay by PayPal. I called to custom service of PayPal. The custom service said your website don’t support PayPal.I am from China. Thank you.
Interesting, it’s odd because many people on my website use PayPal from various countries for payments. May be it’s due to some additional restrictions from China on type of payments. Did you try to pay using pre-loaded balance in your PayPal account?
Also, you can try Stripe, which supports various Credit/Debit cards as well as some other local payment methods based on regions.
Regards, Akbar
Peace be upon you , I discovered a vulnerability in your setup : if any .srt file has a repeating pattern ,the used model -specially Gemini- stop working and issue an error to the user which costs you without charging the user specially if he runs a batch translations ,be vigilant m
Regards ,
Dr.Hossameddeen
Dear Hossameddeen,
Thank you for bringing this to my notice. I have seen this failure intermittently on my website, but never realised that it would be due to repeating pattern. If you would be kind enough to also share some sample file, that would be fantastic. Thanks again!
Regards, Akbar
Peace be upon you ,if you wish I can provide you with a python script to clean .srt files before feeding it to the model ,
That would be fantastic. I really appreciate the effort. If this turn out to be something which is generally helpful to the normal users, I will be more than happy to incorporate taht.
Regards, Akbar
Sure ,this window does not support sending any code , I will email it to you.
I got it, thank you so much!
Peace be upon you , my subtitles is one hour each ,its about 23 subtitles ,your setup did not output any correct file ,I do not want a refund but ask you to reset my balance to the original 6$ to attempt smaller files,
Sincerely,
Dr.Hossameddeen
Sorry for the trouble there Mohsen. Yeah, DeepSeek can sometime be really weird when their server are under pressure. It seems to be have rejected all those API calls. The good news is that you were never charged for these failed translation, and that’s normally the case with any translation on my website. You are only charged after successful translation.
That said I have also top-up some extra for the inconvenience caused. Nothing much, but hopefully enough to help you experiment with this website and other translators too.
Please let me know if run into any other issues or need further assistance. Happy to help there.
Regards, Akbar
Hi this translation gone wrong mPQkL8Is3EXXXXX.HOw can I do to get refund?
Thanks Oliver for reporting this back to me and sorry for the trouble. Looks like something went wrong during the cancellation process and it went into some weird partial yet paid state. I will investigate further to isolate and fix this properly.
I have issued full refund for this order. Sorry again for the trouble.
Regards, Akbar
Hi Akbar,
I’m looking to get receipts for the top up payments that I’ve made through stripe and link not the individual invoices for each translation where do I get these not the individual invoices for each translation where do I get these please please?
Hi Eli R, thanks to your request, this feature is now generally available to all users. They can now get Invoice for any balance top-up from the order history page.
Regards, Akbar
Hi Akbar
I made a payment #3JA73236GXXXX for translation from russian to polish with DeepSeek but the timer froze on 2 minutes and for and hour nothing happened, te progress was 0% so I cancelled it. You wrote that you want a feedback considering deepseek so that is why I leave this comment. Hope you can get to the bottom of this problem.
BR
Sebastian
Really appreciate that you reporting this back to me. Unfortunately, it looks like another one of those instances where few of the DeepSeek API requests just goes in waiting stage for too long and the client time out. I probably need to optimise my automatic re-try mechanism here. But, for now, I think if you don’t see any partial update from my server for 3-4 minutes, there are good chances that it’s not going to finish, so please feel free to cancel and re-try. I know it’s still inconvenient, so, please bear with me, while I improve this further.
PS. As you probably know, any failed translation are not charged – so was the case in. But again, in case of any issues, comments or suggestion, please feel free to reach out. Thanks again!
Regards, Akbar
Hi akbar,
???????
Unfortunately, the translation process failed with the following error:
Error: 429:Resource has been exhausted (e.g. check quota). File: —–.srt
I will be shortly looking into this. If this is a server problem, your money will be refunded in next 1-2 days. If it’s not, please contact me ASAP. In case of any further questions or queries, please feel free to contact me and mention your order#2N4937XXXXX.
Sorry for the trouble. Unfortunately, it’s a temporary error and you should be able to translate on the next try. I’m working on a fix, which should reduce/fix this quote issues. Hopefully will be ready in a day or two.
Regards, Akbar
Hi Akbar, I tried to add credit to my account with multiple bank cards and it says my bank card was not accepted.
How can I add credit to my account with a bank card.
Specifically I tried multiple cards!
Hi Raducu,
Sorry for the trouble and late response. I assume you were trying to top-up using PayPal. Please note that PayPal is very pick about few Credit Cards – at least on my website. I would suggest you to try to do this via Stripe and see if that helps.
Regards, Akbar
Hi Akbar, i’m translating some subtitles from English to Italian and i’m getting this error (the tool was working fine a few days ago):
Unfortunately, the translation process failed with the following error:
Error: Translation doesn’t seem to be working correctly. Is the source and translation language pair valid and supported by OpenAI GPT? Or try changing translation mode to ‘Per-Line’ or ‘Auto-Line’. Please report this issue if you think it’s a server problem.
I’ve tried “Auto-line” and the process was completed, however the translation was full of errors and i couldn’t use it. What should i do?
Sorry for the late reply Pier. I have seen this type of issue on certain content in specific language pair where most of the time the problem lies in automatic splitting and merging of the translated lines. Would it be possible for you to share a copy of the source subtitle (or portion of it) so that I can investigate this further and see if there are any workarounds.
If you were trying this using paid translation, the order number would be enough to get me going.
Regards,
Akbar
Hi Akbar, translating an Italian source file to German and English with OpenAI, I got the following error message: “Unfortunately, the translation process failed with the following error:
Error: This content doesn’t comply with OpenAI’s usage policies and thus can’t be translated. Moderation Category: hate/threatening”
Of course, the source file doesn’t contain any hate or threatening speech. There is also no problem translating it with Deepl or Gemini. Just OpenAI pulls this error message. Please, feel free to have a look at order #W3dA2uXcEw, gd5LlwmHHM4P, WRJgT9L76s. None of them were charged. Thanks!
Thanks for getting back to me and sorry for the trouble there.
Unfortunately, OpenAI is very picky about what content it process and sometime even a single word or sentence would trigger its moderation filtering. I think in this case, it’s tripping over the subtitle line#9 which is just a bit hard language/tone.
It’s annoying for sure, but this not something under the direct developer control – you can’t bypass these moderation filters or risk being flagged by their system for violating their usage policieis.
Gemini also has a moderation layer, but it’s far more lenient, and I don’t think DeepL performs any moderation at all (at least not officially). Which explains why you were able to translate using these tools. So I guess when you run into any moderation issues, the only workaround is to try other translators. I hope in the future they add improve their moderation policies to also take into account the context and type of dialog to make it better.
Thank you for your understanding.
Regards, Akbar
Thank you very much for your feedback and considerations! Good to know about these restrictions in the case of OpenAI! I’ll stick to Gemini and Deepl in this case. I could try to eliminate the word that’s probably provoking the moderation, but I really do not have any hence which word or sentence it could be. Line #9 seems pretty normal to me, a sentence about “Kindergarden”… Anyway, thanks for your reply!
Hi Johannes,
Sorry, I was wrong! Doing some more experimentation, it looks like it’s actually some content between line#19 to 25 which is triggering that moderation category. Though that said, I found that in this case it was actually tripping due to a new moderation category “hate/threatening” added recently by OpenAI, and which I was not fine tuning properly. I have now applied that filters and hopefully it will now let you translate using OpenAI as well.
Thanks you for bringing this to my notice and for patience while I keep improving this tool.
Regards, Akbar
I am having a similar problem to others. Using gemini, paragraph mode some lines are not translated and shifted. Looks like the model is still tripping some orienting paragraph info, order 7NjYPjuNkXXXX
Hi Patrick,
Thanks for reporting this back and sorry for the trouble. Yeah, sometime these models get a batch of the lines so wrong that it’s completely messed up. Unfortunately, there is not a simple workaround to avoid this as due to some inbuilt randomness in the model, it removes the line/row markers, thus making it very hard to restore the correct line/timings back.
The only workaround/fix is to manually review the translation and then shift/re-translate line batches. You can read more about these here:
https://blog.syedgakbar.com/subtitles-translator-help-tips/#retranslate-block
Regards, Akbar
Hi Akbar! Translating from Italian to German with Deepl, I run into some issues: The translator doesn’t translate line per line when “paragraph” is selected in the configurations. Often, he translates several lines from Italian into one single in German. Consequently, leaves lines empty in the translated file. Neither does he keep the line breaks in every single line I checked this twice with the same source file and got the same results, see order #X3yFvDBbrXXXX and #pDcSnZ07XXXXX). Translating the same source file from Italian to English with Deepl, works just fine (#BbTX5aCFXXXX). Why does Deepl present this strange behaviour just with Italian to German, the “mother language” of Deepl?
Hi Johannes, thanks for trying these out and sharing the issue with some example – it was very helpful. Apparently, DeepL translator was skipping/ignoring the splitting tags which were in between a sentences when processing certain language pairs. I guess this problem started happening with the latest language model optimisations. Thanks to your good example, I’m able to further tweak the splitting logic on my end to improve the translation in the paragraph mode for DeepL translator. This now seems to be working reasonably well for me. Can you please give this another try when convenient?
Regards, Akbar
Hi Akbar! Thank you very much for your reply and your efforts to tackle it down.
I checked it with the original Italian subtitle file and also with another one in Italian. Really, I think you solved the problem! It’s working perfectly now. If you’d like to have a look at this two last translation tasks, here are the order numbers:
#BPlgZVrXXXX
#WLMegfgXXXX
Again, thanks a lot. Really great work your site!
Kind regards.
Johannes
Thanks Johannes! I’m glad it fixed the paragraph issues very well.
Regards, Akbar
Akbar, I have to correct myself: Concerning the splitting logic in paragraph mode, it really seems to work well now (Italian to German), but Deepl apparently still ignores line breaks inside the paragraphs (if a subtitle have two lines). The line break tag \N get lost in the translation files in case of German. If translated Italian to English, it’s a bit better, but sometimes Deepl keeps the tag, sometimes only part of it (only the back slash \) and sometimes ignores it completely. Also hyphens are sometimes ignored (in case of dialogue). See line 74 in order #BbTX5aCXXXXX (this order contains two translation tasks, one to German and the other to English, see the English one).
Thanks Johannes! This is an interesting one. There are two problems here. First is that I’m not sure that “\N” for line-break is the standard SRT specification. I tried exploring various standards and extensions of the SRT format, and none clearly documents this line splitting behaviour:
https://en.wikipedia.org/wiki/SubRip
That said, if the DeepL doesn’t handle this line-break correctly, I’m not surprised. It can be only configured to ignore certain types of XML tags – but not any individual string or character patterns. So I’m out of luck there as well.
However, I went with a intermediate workaround for now and that’s I’m replacing the \N with actual line-break character before translation. This seems to keep the DeepL translator happy and it brings in correct translation in most of the cases. The only concern I have is that it may cause problem for some other content which needs this \N character in place, but I guess I can see when that’s needed and then use any other encoding technique. For now this will at least get you some good results.
Thanks again and as always if you run into any further issues, happy to help.
Regards, Akbar
Great, thanks a lot for your workaround! About the “\N” question: I do not know either what’s really the standard specification here, Aegisub is using this string for line breaks, other tools like Tero Subtitler or youtube do use some line break tag, but not visibly, so I do not know what’s the code behind of it to keep manually set line breaks in place. Meanwhile, I guess, for my purposes, concerning the Italian-German language pair, Gemini 1.5 Pro gives the best translation results in accuracy and also fidelity. It’s really amazing to see the level in which Gemini 1.5 is considering inherent context of the source text. GPT 4o seems to be on a similar level. If I would do an actual ranking list for myself, Deepl would get on the last place…
Thanks Johannes for the feedback and sharing your thoughts. Yeah, it’s amazing to see how the machine translation have evolved – especially since introduction of the large-language-models in the recent years. When I started working on this hobby projects nearly 10 years ago, the translation for most of the Asian language was really bad – it was mostly word-by-word translation, without keeping any context and/or language flow. And now we have come to a point where these machine translations are almost 80-90% accurate for most of the populate languages. And I can only see these improving insanely fast now. A bit scary, but this is an era of AI 🙂
Regards, Akbar
hello akbar,
i am enjoying translating using your subtitle tool.
a little problem though.
i am translating english to hebrew. and the second line in the translation does is not so successful like the first one-Punctuation marks such as exclamation marks, periods and commas are not where they should be – from right to left, but appear in reverse from left to right.the first line is always ok!
would love your help with this.
thank you.
Hi Effi, thanks for the feedback. Regarding your issue, can you please confirm if the “Embed Language Bi-Directional codes” is turned ON you in the settings (upper right-corner of the web-page)? Also, I would suggest, if not already doing, is to change alignment of the translated subtitles to right. If still run into any issue, a 2-3 line samples of it would be helpful in isolating and fixing the problem properly.
Regards, Akbar