Skip to main content

​
OpenAISTT

OpenAI speech-to-text (STT) transcriber.

​
Constructor

​
apiKey
string | null
OpenAI API key. Defaults to the OPENAI_API_KEY environment variable.
​
model
OpenAISTTModel | string
Transcription model id. Default 'gpt-4o-transcribe'.
​
language
string
Spoken language as a BCP-47/ISO code. Default 'en'.
​
stream
boolean
Stream partial transcripts as audio arrives. Default true.
​
inputSampleRate
number
Sample rate (Hz) of the audio sent in. Default 48000.
​
outputSampleRate
number
Sample rate in Hz that input audio is resampled to. Default 24000.
​
prompt
string | null
Optional prompt to bias transcription. Default null.
​
turnDetection
string
Turn-detection mode. Default 'server_vad'.
​
vadThreshold
number | null
VAD speech-probability threshold. Default null (provider default).
​
vadPrefixPaddingMs
number | null
Audio padding (ms) prepended before detected speech. Default null.
​
vadSilenceDurationMs
number | null
Trailing silence (ms) that ends a turn. Default null.
​
noiseReduction
string | null
Noise-reduction profile, e.g. 'near_field'/'far_field'. Default 'near_field'.
​
responseFormat
string
Transcript response format. Default 'json'.
​
baseUrl
string | null
Override the API base URL. Default null.

​
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>

​
OpenAISTTModel

Supported OpenAI STT transcription model ids.