Frequently Asked Questions (F.A.Q.)

When you upload your video/audio file, it is first processed and converted to a more suitable format for Automatic Speech Recognition (ASR) engine on the secure cloud systems. Then speechtext.io extracts speech from within your video/audio files by using state-of-art ASR engines at the background. After it is transcribed, result is presented within an online speech-text editor so you can edit your transcription and download it to your PC.

There is no cost to using the default Speechtext.io (demo version). You get 10 minutes of transcription for free when you first sign. After your free minutes, you can buy as many minutes as you want, statting from $9. Remember, the more you buy, the less you pay! For enterprise plan, please contact us!
You can easily create your account and make use of 10 minutes of free transcription with demo account. Once you tried our service, we believe that you will like its functionality and accuracy. For more than 10 minutes transcription, you will need to go to our paid plans which offers best price for transcription among competitors.
Yes, there is an educational discount available to those who provide verification. All you need to do is, create SpeechText.io account with your university/college email account and email us at [email protected] to claim student/researcher discount. When it is approved, you can get %20 discount for your all orders for 1 year.
For that case, you should consider our enterprise plans that offer better price and extra functionalities. To get the best offers you can contact us at [email protected]. We will be happy to hear from you.
We support 120 languages including English, Turkish, Arabic, Russian, Spanish and many more. We also support different dialects of the languages like Spanish and Arabic. We will be ready to help for transcribing in your language.
To get the best transcription results, you should upload high quality audio/video. To do that, record your interviews or survey in a quiet environment with less background noise, ensure your speakers to speak clearly and separately. Additionally, you can provide context information about the speech by entering keywords while uploading your files. This context information is used to feed ASR engines to improve automatic transcription results.
As SpeechText.io, we can transcribe most of audio and video file formats including, but not limited to:
  • Popular audio file formats: *.mp3, *.mp4, *.m4a, *.aac, and *.wav
  • Popular video file formats: *.mp4, *.wma, *.mov, and *.avi
If your file format isn’t listed, please feel free to contact us ([email protected]).
As an automated system, we don’t claim that your transcript will be 100% accurate but trying to be as accurate as possible. With high quality audio files, you can get your transcripts up to %95 accuracy rate. To finalize your transcript and make it perfect, we provide an online editor that you can easily edit your transcript file. In order to help you, we also highlight the words that we are not so sure about.
SpeechText.io online embedded editor works together audio and text. This lets you to edit or correct your transcripted text while listening to your record. You can update, delete, and adjust words and phrases and SpeechText.io will continue to put timestamps.
Yes you can export your transcripted files in .txt, .srt, .docx formats. If you need another file format, please contact us at [email protected]ext.io.
 
The length and size of your audio or video file is the main determinant of transcription time. After your file upload is finished, it takes 5-10 minutes to complete 1 hour audio approximately. Good news is you don’t need to wait for transcription to finish, since SpeechText.io sends a notification email when it is ready.