Skip to main content

AssemblyAISTT

AssemblyAI speech-to-text provider. Creates a configured AssemblyAI streaming STT provider for use in a voice agent.

Constructor

apiKey
string | null
AssemblyAI API key. Falls back to the ASSEMBLYAI_API_KEY env var, then null.
language
string
Transcription language code. Default: 'en-US'.
inputSampleRate
number
Input audio sample rate in Hz. Default: 48000.
targetSampleRate
number
Target output sample rate in Hz (alias of outputSampleRate). Default: 16000.
outputSampleRate
number
Output audio sample rate in Hz. Default: 16000.
encoding
string
Audio encoding. Default: 'pcm_s16le'.
formatTurns
boolean
Whether to apply turn formatting (punctuation/casing). Default: true.
keytermsPrompt
string[] | null
Keyterms to bias recognition toward. Default: null.
endOfTurnConfidenceThreshold
number
Confidence threshold for declaring end of turn. Range 0-1. Default: 0.4.
minEndOfTurnSilenceWhenConfident
number
Minimum silence (ms) before end of turn when confidence is high. Default: 560.
maxTurnSilence
number
Maximum silence (ms) allowed within a turn. Default: 2400.
speechModel
AssemblyAISTTModel | string
Speech model to use. Default: 'universal-streaming-english'.
languageDetection
boolean
Enable automatic language detection. Default: false.
baseUrl
string | null
Override the provider base URL. Default: null.
region
string
Service region. Default: 'US'.

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>

AssemblyAISTTModel

Supported AssemblyAI STT model names.