Avis et commentaires
TranscribeX
•
65 classements
Jean-Jacques Larrea
3 mars 2026
Version de l'application : 4.9
What an excellent app! I used it with the Parakeet model which is moderate in size yet yielded an accurate transcription from a very noisy phone recording. I was able to use the Pyannote engine to assign speakers, and post-facto change the speaker names. Export provided many different possible formats including Markdown (which was perfect for entering into an LLM for analysis) with options for whether to include speakers and/or timestamps. I would not hesitate to recommend this app.
Hakan
25 févr. 2026
Version de l'application : 4.9
Very buggy, undo redo does not work, text disappears whil merging
Réponse du développeur
28 févr. 2026
Hey, you can use Cmd+x for undo, and Cmd+Shift+x for redo. These are standard macOS shortcuts and works in TranscribeX as well.
Jaime
9 févr. 2026
Version de l'application : 4.7
It has been a very good experience. Transcription is quickly and accurate enough.
Gerónimo Soto Gómez
30 janv. 2026
Version de l'application : 4.5
It’s so good, but i think we all need an option to adjust the words output. I use it for editing clips and an option to adjust the word lenght would be amazing. Thks.
Réponse du développeur
31 janv. 2026
Hey, thanks for the feedback. Can you email me some details about the word length requirement please? You can check the REFLOW function which might be what you needed.
Lolo
15 janv. 2026
Version de l'application : 4.0
I thought I would be able to generate a summary of meetings embeded into templates but it’s just a transcription. Either I haven’t found the features or it’s not what I expected for. In any case the transcription is done correctly and the translation feature is also nice.
Réponse du développeur
15 janv. 2026
Hey, there is AI Summary if you turn on the toggle in Transcription setting page. We are also adding the ability to export the Summary and Actions into a text file. Plus, customising which AI Service will be used for the AI Summary. Since this is just a feature request, I wonder if you could change the negative feedback to positive, or at least not a negative? Thanks so much.
尤国淳
4 janv. 2026
Version de l'application : 3.7
无法下载模型,下载一半卡住不动了
Réponse du développeur
7 janv. 2026
Hey, you might have to use a VPN in China to download the models as they are all from huggingface.
Micheal
25 déc. 2025
Version de l'application : 3.6
中文无法识别,导出空白
Réponse du développeur
27 déc. 2025
你好,可以发个email到[email protected]吗?你用那个中文的whisper模型应该是没有问题的,我自己试过,不是所有的模型都支持中文的。
Сергей Герасименко
2 mars 2026
Version de l'application : 4.9
will not save the transcription, does not always work, the translation is not of high quality
Jeremy Ward
23 févr. 2026
Version de l'application : 4.7
I’m finding this app great so far! I work as a counsellor and have permission to transcribe session audio where I can keep data private and secure. TranscribeX works great for this handling all data locally. One thing I’d appreciate would be some online documentation to help me understand a little more about how features like Diarisation and Voice Profiles work. So far I’ve done some experiements. But in a marriage counselling session it identified 7 speakers instead of 3. I’m not quite sure how to refine from that point forward.
Réponse du développeur
25 févr. 2026
Thanks so much for the feedback — really glad TranscribeX is working well for your sessions and privacy needs. Good point on documentation for diarisation and voice profiles — I’m working on this. The extra speakers usually come from tone or pause changes; What you can do is just merging the speakers manually. There is a voice sample for each speaker you can easily tell who they are. Really appreciate you sharing this!
Sebastião Lustosa
7 févr. 2026
Version de l'application : 4.7
PERFEITO!
Felipe Neri
23 janv. 2026
Version de l'application : 4.0
Very good! I love it!
Daniel Masters
14 janv. 2026
Version de l'application : 3.7
Works very well and much better than the other transcription apps on here. It’s nice that it’s local too!
samuel “Samlin” linhares
31 déc. 2025
Version de l'application : 3.7
Até o momento o melhor App de transcrição que conheço!
Herman Sandoval
22 déc. 2025
Version de l'application : 3.6
I tested more than one hundred files in Spanish and English and obtained very good transcriptions. Parakeet is really fast and produces good transcripts. Finally I was able to transcript many audios of courses I did some years ago. Some weird things I found: - Memory is not being freed when a transcription is finished. The app ended up using more than 42 GB of RAM and caused my laptop to freeze multiple times. When bulk exporting, I had to select smaller folders and close and reopen the app before starting another bulk export. - At the beginning I had two models downloaded: Whisper and Parakeet. When I bulk exported a folder, all the transcripts were generated using Whisper even though I had selected Parakeet as the transcription model. I had to leave only one model to avoid this error. Thanks for this great tool, it is very useful.
Réponse du développeur
22 déc. 2025
Thanks for the detailed feedback and for testing it so thoroughly — really glad to hear the transcription quality and speed worked well for you. I’ll look into the RAM usage and optimise the RAM performance in the next version.
Jackie
28 févr. 2026
Version de l'application : 4.9
I’m a huge fan of this app! Would you consider allowing users to integrate their own LLM models and diarization engines? Having the ability to customize these workflows would make this an essential, permanent part of my daily toolkit. Thanks for your time and for a great product!
Réponse du développeur
28 févr. 2026
Thanks so much. I am happy that app is useful for you. Yes, you can definitely use your own LLM models, just install Ollama or LMStudio and run your own LLM models, then create an AI Service in the TranscribeX setting page for it. For the diarization, I am not really sure actually, but I am using the most popular ones Pyannote and Sortformer. If there is any other options, please let me know, I can integrate it into the app. It's all running locally anyway.
Jarrod Job
9 févr. 2026
Version de l'application : 4.5
Awesomes - Overall intuitive interface, love the product vision of speaker identification + profiles + diatrisation is nice as well. My biggest requests - (1) training the same voice speaker voice profile over and over and over, rather than duplicates of the voice profile. (1.1) The workflow of initial transcribe to reflow (with the right settings) to diatrisation to speaker application to saving speaker voice profiles is not there. Visualizing this out in the UI would be incredible. Features I don’t use b/c I am not confident - Screen-recording in my opinion is not there yet unless you are using a Mac Studio or a $2500 computer. There are opportunities to lower resolution, but I still have challenges on an M3 MBP with 16 GB while on a call.
Réponse du développeur
10 févr. 2026
Thank you so much for the detailed feedback. This is incredibly helpful. You’re absolutely right about the voice profile. We will investigate what can be improved. For the workflow, it's really a great idea. A guided pipeline-style UI would be incredible. Feature request accepted. It's a bit challenge to have a perfect UI for this though. For the screen-recording, it's actually not very resource-consuming, lots of uses use it to record meetings, transcribe, diarise, and summarise without even open the Transcribe main page. It happens silently in the background.
Jay Kay
3 févr. 2026
Version de l'application : 4.5
Actually amazing, have transcribed 800 hours of files this week, working on a large project. This app has made that somehow not be a nightmare, perfectly written and great frontend.
Giangiacomo Fanizzi
19 janv. 2026
Version de l'application : 4.0
Simple, effective, and comprehensive.
Tom Kerswill
5 janv. 2026
Version de l'application : 3.7
This works great, and seems easy to use.
Maurizio
30 déc. 2025
Version de l'application : 3.7
ottima …