Rate this page:

Google

List of Google ASR models. Can be passed via the ASRParameters.model parameter.
NOTE: the enhanced models cost more than the standard rate.
Add the following line to your scenario code to use the enum:

require(Modules.ASR);

Consts

DEFAULT: ASRModel

Best for audio that is not one of the specific audio models. For example, long-form audio. Ideally the audio is high-fidelity, recorded at a 16khz or greater sampling rate.

command_and_search: ASRModel

Best for short queries such as voice commands or voice search.

command_and_search_enhanced: ASRModel

Command_and_search model with more accurate recognition.

default_enhanced: ASRModel

Default model with more accurate recognition.

phone_call: ASRModel

Best for audio that originated from a phone call (typically recorded at a 8khz sampling rate).

phone_call_enhanced: ASRModel

Phone_call model with more accurate recognition.

video: ASRModel

Best for audio that originated from video or includes multiple speakers. Ideally the audio is recorded at a 16khz or greater sampling rate.

video_enhanced: ASRModel

Video model with more accurate recognition.