Deepgram
List of Deepgram ASR models.
Add the following line to your scenario code to use the enum:
require(Modules.ASR);
Constants
conversational
Optimized to allow artificial intelligence technologies, such as chatbots, to interact with people in a human-like way.
default
The default General model.
finance
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
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
Optimized for everyday audio processing.
general_enhanced
Optimized for everyday audio processing. Applies the newest ASR module with higher accuracy.
meeting
Optimized for conference room settings, which include multiple speakers with a single microphone.
meeting_enhanced
Optimized for conference room settings, which include multiple speakers with a single microphone. Applies the newest ASR module with higher accuracy.
nova2_atc
Optimized for audio from air traffic control.
nova2_automotive
Optimized for audio with automative oriented vocabulary.
nova2_conversationalai
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
Optimized for audio sources from drivethrus.
nova2_finance
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
Optimized for everyday audio processing.
nova2_medical
Optimized for audio with medical oriented vocabulary.
nova2_meeting
Optimized for conference room settings, which include multiple speakers with a single microphone.
nova2_phonecall
Optimized for low-bandwidth audio phone calls.
nova2_video
Optimized for audio sourced from videos.
nova2_voicemail
Optimized for low-bandwidth audio clips with a single speaker. Derived from the phonecall model.
nova_general
Optimized for everyday audio processing.
nova_phonecall
Optimized for low-bandwidth audio phone calls.
phonecall
Optimized for low-bandwidth audio phone calls.
phonecall_enhanced
Optimized for low-bandwidth audio phone calls. Applies the newest ASR module with higher accuracy.
video
Optimized for audio sourced from videos.
voicemail
Optimized for low-bandwidth audio clips with a single speaker. Derived from the phonecall model.