GoogleSTT
Google Cloud speech-to-text (STT) provider.Constructor
Google API key. Falls back to the
GOOGLE_API_KEY environment variable, then null.Recognition language(s) as BCP-47 tags (e.g.
'en-US'), a single string or an array (joined with commas). Default 'en-US'.Recognition model. Default
'latest_long'.Input audio sample rate in Hz. Default
48000.Service-account credentials, as a raw JSON string or parsed object. Default
null.Path to a service-account JSON key file. Read when
credentialsJson is not provided.Google Cloud project id. Default
null (derived from the service-account JSON when omitted).Recognizer location/region. Default
'us'.Use streaming recognition. Default
true.Number of audio channels in the input. Default
1.Emit interim (non-final) transcription results. Default
true.Add automatic punctuation to transcripts. Default
true.Filter profanity from transcripts. Default
false.Recognize spoken punctuation (e.g. “comma” -> ”,”). Default
false.Recognize spoken emojis. Default
false.Include per-word start/end time offsets. Default
false.Include per-word confidence scores. Default
false.Maximum number of recognition alternatives to return. Default
1.Emit voice-activity (speech begin/end) events. Default
false.Timeout in seconds to wait for speech to start. Default
null (no timeout).Timeout in seconds of silence marking speech end. Default
null (no timeout).Minimum number of speakers for diarization. Default
null.Maximum number of speakers for diarization. Default
null.Minimum confidence threshold for accepting results,
0.0-1.0. Default 0.0.