GladiaSTT
Gladia speech-to-text (STT) provider.Constructor
Gladia API key used to authenticate requests.
Defaults to the
GLADIA_API_KEY environment variable, or null if unset.Gladia transcription model to use.
Preferred transcription language(s) as language codes/names. Only the
first entry is used to select the active language. When empty or omitted,
the language defaults to
'english'.Enable automatic detection and switching between languages within a single
stream (multilingual audio).
Sample rate, in Hz, of the audio fed into the provider.
Sample rate, in Hz, used for the transcription stream. This value is also
used as the effective sample rate.
Audio encoding format of the input stream (e.g. PCM encodings).
Bit depth of the input audio samples (e.g.
16).Number of audio channels in the input stream (e.g.
1 for mono).Whether to emit interim/partial transcripts as audio is still being
processed, in addition to final transcripts.