Frequently Asked Questions

Do you have any question about Aditu service? We have some answers prepared.

The success rate depends on factors such as audio quality, echoes, noise or background music, type of speech, register, whether it is dealing with standard language or a variant, volume, speed… Under optimal conditions, the success rate can exceed 95 % (see demos).

To get the best transcription results, make an effort to have the following characteristics in your recording:

  • A good microphone (directional, eliminating ambient sound, using earphones...)
  • Without echoes or noise
  • Absence of background music (or with this on a different track)
  • Correct and complete sentences, with no repetitions, corrections or hesitations
  • Formal register
  • Standard language
  • A single speaker
  • Adequate volume, neither too loud nor too soft
  • Proper speed, neither too fast nor too slow

On uploading the file, you can indicate the voice track, if this is separated

Live transcription is more complex and this may reflect in the results. The best way to know is to try, since each case has its features. In any event, if you do not need a live transcription, you can always record your voice first and send it for transcription afterwards.

It accepts the most usual audio and video formats, such as WAV, MP3, MP4, MOV, WEBM, etc. You can also record from the website using the microphone on your computer or phone, without having to prepare any file.

Aditu recognises Euskera and Spanish, for now. Not bad for a new effort, isn’t it?

In the case of uploaded files, it will depend on the server load, but it will normally take much less time than the duration of the file.

In live transcription from the microphone, Aditu will be transcribing as you talk, so that when the recording stops, the transcription will be ready.

Aditu will provide you with:

  • The transcription of the speech in unformatted text.
  • A subtitle file (i.e., the transcription and the time stamps for each sentence or phrase, so that conventional audio or video players or web browsers can understand and display them) in different formats: SRT, VTT, etc.
  • Transcription with time stamps for each word (for example, for advanced searches in video).

Numbers, times, dates, abbreviations, acronyms, capitals, lowercase and punctuation signs ... will be correctly transcribed in all of them.

Once registered, you will enjoy a time credit of 5 minutes free of charge.

Over the website or from your account, you can purchase more credit under different plans and prices. If you need more hours or prefer to buy a periodic subscription (a specific number of hours per week or per month), get in touch with us.

Indeed, you can integrate Aditu into your work flow, application, CMS, etc. by means of nuestra API. We also have an API for live transcription, to be integrated into your virtual assistant, to subtitle live events, etc.

The confidentiality of your data is guaranteed. If you need greater speed, we can install Aditu speech recognition in your servers. If you are interested, get in touch with us.

For questions not answered in this section, contact us.