AbstractAbstractGetThe driver's transcription models.
AbstractGetThe names of the methods this driver implements.
AbstractSpeechTranscribes the audio in params.audioData (or the base 64 params.audioFile). On success the
transcript is in SpeechResult.content, and SpeechResult.usage carries the audio duration in
Seconds when the provider reported one.
Base class for speech-to-text models: recorded audio in, a transcript out. Drivers are resolved through the ClassFactory for
MJ: AI Modelsof typeSpeech to Text, keyed by the model vendor'sDriverClass, and are run byAISpeechToTextRunnerin@memberjunction/ai-prompts.Split from
BaseAudioGenerator, which also carries text-to-speech. A driver that does both registers against this class andBaseTextToSpeechunder the same key. Drivers that split oversized audio call TranscribeAudioWithSplitting.