Welcome to YobiYoba, a speech recognition service to transcribe audio and video recordings.


A simple pay as you go pricing scheme

12 ¢ /Min

  •  No minimum fee per file, i.e. you only pay for the seconds that are processed
  •  For audio files, you only pay for the amount of transcribed speech, not for the file duration
  •  No extra fee to manage, edit, or convert your transcripts
  • Need a Paypal account or a coupon

Speech to text conversion is the process of converting spoken words into written texts. YobiYoba voice-to-text conversion process is done in 3 steps. First our software identifies the audio segments containing speech, then it recognizes the language being spoken if it is not known a priori, and finally it converts the speech segments to text and time-codes. The transcription result is an XML document which we then convert on-demand to various text and subtitling formats including PDF, RTF, CSV, SRT or VTT.

It is important to understand that like any other pattern recognition technology, speech recognition cannot be error free. We therefore provide an editing tool to manually modify or correct the automatic transcripts. You can also help the transcription process by providing a list of uncommon words which are specific to your data (such as proper names). To get event better results, you can provide some plain text closely related to the audio data.