Rate this page:

Deepgram

List of Deepgram ASR models. Can be passed via the ASRParameters.model parameter.
Add the following line to your scenario code to use the enum:

require(Modules.ASR);

Consts

DEFAULT

Copy URL
DEFAULT: 

ASRModel

The default General model.

conversational

Copy URL
conversational: 

ASRModel

Optimized to allow artificial intelligence technologies, such as chatbots, to interact with people in a human-like way.

finance

Copy URL
finance: 

ASRModel

Optimized for multiple speakers with varying audio quality, such as might be found on a typical earnings call. Vocabulary is heavily finance oriented.

finance_enhanced

Copy URL
finance_enhanced: 

ASRModel

Optimized for multiple speakers with varying audio quality, such as might be found on a typical earnings call. Vocabulary is heavily finance oriented. Applies the newest ASR module with higher accuracy.

general

Copy URL
general: 

ASRModel

Optimized for everyday audio processing.

general_enhanced

Copy URL
general_enhanced: 

ASRModel

Optimized for everyday audio processing. Applies the newest ASR module with higher accuracy.

meeting

Copy URL
meeting: 

ASRModel

Optimized for conference room settings, which include multiple speakers with a single microphone.

meeting_enhanced

Copy URL
meeting_enhanced: 

ASRModel

Optimized for conference room settings, which include multiple speakers with a single microphone. Applies the newest ASR module with higher accuracy.

nova2_atc

Copy URL
nova2_atc: 

ASRModel

Optimized for audio from air traffic control.

nova2_automotive

Copy URL
nova2_automotive: 

ASRModel

Optimized for audio with automative oriented vocabulary.

nova2_conversationalai

Copy URL
nova2_conversationalai: 

ASRModel

Optimized for use cases in which a human is talking to an automated bot, such as IVR, a voice assistant, or an automated kiosk.

nova2_drivethru

Copy URL
nova2_drivethru: 

ASRModel

Optimized for audio sources from drivethrus.

nova2_finance

Copy URL
nova2_finance: 

ASRModel

Optimized for multiple speakers with varying audio quality, such as might be found on a typical earnings call. Vocabulary is heavily finance oriented.

nova2_general

Copy URL
nova2_general: 

ASRModel

Optimized for everyday audio processing.

nova2_medical

Copy URL
nova2_medical: 

ASRModel

Optimized for audio with medical oriented vocabulary.

nova2_meeting

Copy URL
nova2_meeting: 

ASRModel

Optimized for conference room settings, which include multiple speakers with a single microphone.

nova2_phonecall

Copy URL
nova2_phonecall: 

ASRModel

Optimized for low-bandwidth audio phone calls.

nova2_video

Copy URL
nova2_video: 

ASRModel

Optimized for audio sourced from videos.

nova2_voicemail

Copy URL
nova2_voicemail: 

ASRModel

Optimized for low-bandwidth audio clips with a single speaker. Derived from the phonecall model.

nova3_general

Copy URL
nova3_general: 

ASRModel

Optimized for everyday audio processing.

nova3_medical

Copy URL
nova3_medical: 

ASRModel

Optimized for audio with medical oriented vocabulary.

nova_general

Copy URL
nova_general: 

ASRModel

Optimized for everyday audio processing.

nova_phonecall

Copy URL
nova_phonecall: 

ASRModel

Optimized for low-bandwidth audio phone calls.

phonecall

Copy URL
phonecall: 

ASRModel

Optimized for low-bandwidth audio phone calls.

phonecall_enhanced

Copy URL
phonecall_enhanced: 

ASRModel

Optimized for low-bandwidth audio phone calls. Applies the newest ASR module with higher accuracy.

video

Copy URL
video: 

ASRModel

Optimized for audio sourced from videos.

voicemail

Copy URL
voicemail: 

ASRModel

Optimized for low-bandwidth audio clips with a single speaker. Derived from the phonecall model.