PROCESSING OF AUDIO RECORDINGS IS UP TO X50 TIMES FASTER THAN ITS LENGTH

AVAILABLE SPEECH MODELS

We can adapt existing language and acoustic models to any subject area to improve recognition quality.

TECHNICAL FEATURES

Supported languages

  • Russian (Cloud/On-Premise)
  • English (Cloud/On-Premise)
  • Kazakh (Cloud/On-Premise)
  • Uzbek (Cloud/On-Premise)

Audio data formats

Telephony (phone):

Wav PCM, 8 kHz /16 bit

Media (broadcast):

Wav PCM, 16 kHz /16 bit

Audio requirements

All major formats and codecs WAV, AAC, OGG, MP3, WMA, MuLaw, ALaw, Linear16, RawOpus are supported and automatically converted into WAV.

Recognition accuracy

Russian:
  • Telephony up to 95%
  • Media up to 98%
English:
  • Telephony up to 85%
  • Media up to 87%
Kazakh:
  • Telephony up to 95%
  • Media up to 97%
Uzbek:
  • Telephony up to 95%
  • Media up to 98%

Test it for free!

bg-form

Evaluate the quality and speed of speech recognition on your own audio recordings

Thank you for contacting us, we will contact you soon!

By clicking the button, you agree to the privacy policy.