Speech-To-Text transcribes words spoken in audio into text.
Configuration Parameter | Description |
---|---|
AlternativeWordsThreshold | A threshold that alternative words must meet to be included in the output. |
CustomLanguageModel | The identifier and interpolation weight of each custom language model to use. |
CustomWordDatabase | The name of a custom word database to use. |
FilterMusic | Specifies whether to include speech-to-text results for audio segments identified as music or noise. |
Input | The audio track to process. |
LanguagePack | The language pack to use. |
MatchWords | A comma-separated list of words to tag in the speech-to-text output. |
MatchWordsAddUnknown | Specifies whether to add any unknown MatchWords to the language resource. |
MatchWordsCaseSensitive | Specifies whether matches between MatchWords and the speech-to-text output are case-sensitive. |
MatchWordsThreshold | The minimum score that is necessary for an alternative word to be considered a match to one of the words specified by MatchWords . |
NumParallel | The maximum number of audio segments to process concurrently. |
SampleFrequency | The sample frequency of the audio to send to the audio service. |
SpeedBias | Specifies whether to prioritize processing accuracy or speed. |
SyncDatabase | Specifies whether to synchronize with the training database before beginning the analysis task. |
Type | The analysis engine to use. Set this parameter to SpeechToText . |
Output track | Type | Description |
---|---|---|
Result
|
SpeechToTextResult | Contains a record for each word. |
Field name | Type | Description |
---|---|---|
id | UUID | A universally unique identifier to identify the section of audio described by the record. |
text | TextData | The spoken word converted to text. |
confidence | Int | The confidence score for the speech-to-text process. |
matched | Boolean | Specifies whether the word (or an overlapping alternative that exceeds MatchWordsThreshold ) is in the list specified by MatchWords . |
|