AssemblyAISTT
AssemblyAI speech-to-text provider. Creates a configured AssemblyAI streaming STT provider for use in a voice agent.Constructor
AssemblyAI API key. Falls back to the
ASSEMBLYAI_API_KEY env var, then null.Transcription language code. Default:
'en-US'.Input audio sample rate in Hz. Default:
48000.Target output sample rate in Hz (alias of
outputSampleRate). Default: 16000.Output audio sample rate in Hz. Default:
16000.Audio encoding. Default:
'pcm_s16le'.Whether to apply turn formatting (punctuation/casing). Default:
true.Keyterms to bias recognition toward. Default:
null.Confidence threshold for declaring end of turn. Range
0-1. Default: 0.4.Minimum silence (ms) before end of turn when confidence is high. Default:
560.Maximum silence (ms) allowed within a turn. Default:
2400.Speech model to use. Default:
'universal-streaming-english'.Enable automatic language detection. Default:
false.Override the provider base URL. Default:
null.Service region. Default:
'US'.