Transcription
What is the price?
For our prices, please refer to our pricing page.
Do you offer services in other languages?
Yes, we do. Our software supports 39 different languages and we manually transcribe through our network of professional transcribers in 15 different languages, but if you have a request for another language please contact us through our contact form.
Do you provide bulk discounts?
Yes, we are able to offer a special rate for requests above 100h. Please request a quote here.
Will different speakers be distinguished?
In the transcript, different speakers will be indicated as “speaker 1”, “speaker 2”, etc. You can rename speakers in the online editor.
Do you transcribe files with multiple speakers?
Yes, our software can transcribe multi-speaker files and can also distinguish different speakers in the transcript. Different speakers will be indicated as “speaker 1”, “speaker 2”, etc. You can rename speakers in the online editor.
Do you add timestamps?
Yes, our software automatically adds timestamps, which you can edit if you wish to do so in our online editor.
How can I improve the accuracy of the transcript?
The accuracy can be improved by ensuring that the quality of the audio in your file is the best it can possibly be. Want to know how to optimize your audio? Read it here!
Which languages are supported?
The Amberscript AI currently supports 39 languages.
How long does it take to transcribe my files to text?
Our speech AI delivers results in less than an hour (depending on the size of the file, it can also just take a few minutes). Just upload your audio into our system and we will notify you as soon as the file is ready! If you would like to learn about turnaround times for our manual transcription services, click here.
How do I export my transcript?
To export your transcript, simply click the “Export” button in the online editor on the top left of the screen. Choose your preferred text format in the pop-up screen and then click export and your text file will automatically download.
Can you transcribe audio with foreign accents?
Yes, our software is constantly being trained to pick up on accents and know how to understand them. Want to know more about how this works? Read it here!
What file formats are accepted?
Our software supports all popular audio and video formats, including MP3, MP4, WAV, AAC, WMA and M4A.
How do you keep my files secure and confidential?
Amberscript’s IT infrastructure is built on the server infrastructure of Amazon Web Services located in Frankfurt, Germany. All data that is processed by Amberscript will be stored and processed on highly secured servers with regular back-ups on the same infrastructure.
What happens to the files that I upload?
Amberscript’s IT infrastructure is built on the server infrastructure of Amazon Web Services located in Frankfurt, Germany. All data that is processed by Amberscript will be stored and processed on highly secured servers with regular back-ups on the same infrastructure.
What is the turnaround time?
Our state-of-the-art speech engine delivers results in less than an hour (depending on the size of the file, it can also just take a few minutes). Just upload your audio into our system and we will notify you as soon as the file is ready! if you would like to learn about turnaround times for our manual transcription services, click here.
What is the difference between “Clean read” and “Full verbatim”?
In short, “clean” transcription leads to transcripts that are easy to read and do not contain any repetitions or stutters. “Verbatim” transcription is more comprehensive, as it contains everything that can be heard in the audio/video file. Want to know more about the differences and types of transcription? Read our blog post!
In which formats can I export my transcript?
Our software allows you to export your transcript as a JSON, Word, VTT, SRT, EBU-STL or Text file.
How much editing do I need to do myself?
The machine-made transcription service gives you access to the software and the editor, where you can edit the automatically generated transcription yourself. If you would like to request one of our language experts to review the text for you, check our human-made transcription service.
How do automatic transcription services work?
In a few words, the software “listens” to the audio, identifies the words used and returns it into a text format. That is possible through the use of sophisticated speech recognition technology. In brief, such systems are composed of acoustic and linguistic components running on one or several computers. You can read more about it here.
What is an automatic transcription service?
Automatic Transcription is the process where AI engines analyze audio recordings and automatically convert it into text, generating transcripts with the words said in each second of the recordings. It is similar to the work done by transcribers but in this case it is done by a speech to text software.