Skip to main content

​
NvidiaSTT

NVIDIA Riva speech-to-text (STT) provider.

​
Constructor

​
apiKey
string
NVIDIA API key. Falls back to the NVIDIA_API_KEY environment variable when omitted.
​
model
string
Riva ASR model identifier.
​
server
string
Riva endpoint host. Accepted for compatibility; currently has no effect.
​
functionId
string
NVIDIA NIM function ID. Accepted for compatibility; currently has no effect.
​
languageCode
string
default:"en-US"
BCP-47 language code for transcription (e.g. 'en-US').
​
sampleRate
number
default:"16000"
Input audio sample rate, in hertz.
​
useSsl
boolean
Whether to use a secure (SSL/TLS) connection. Accepted for compatibility; currently has no effect.
​
profanityFilter
boolean
Whether to mask profanity in transcripts. Accepted for compatibility; currently has no effect.
​
automaticPunctuation
boolean
Whether to add automatic punctuation to transcripts. Accepted for compatibility; currently has no effect.

​
close

Release any resources held by the provider.

​
closeEmitter

Close the emitter: drop all handlers and stop emitting. Waits up to 2 seconds for in-flight async handlers to settle before returning.

​
emit

​
event
string
required

​
getRuntimeConfig

​
returns
Record<string, any>

​
listenerCount

​
event
string
required
​
returns
number

​
off

​
event
string
required
​
handler
EventHandler
required

​
on

​
event
string
required
​
handler
EventHandler
required
​
returns
EventHandler

​
once

​
event
string
required
​
handler
EventHandler
required
​
returns
EventHandler

​
onSttTranscript

Register a callback to receive transcripts as they are produced.
​
callback
SttTranscriptCallback
required

​
processAudio

Process a buffer of audio frames. Override in a custom provider.

​
removeAllListeners

​
event
string

​
streamTranscribe

Transcribe a streaming audio source, yielding STTResponses. Override in a custom provider.
​
returns
AsyncIterator<STTResponse>