Inworld STT — supports both streaming (bidirectional WebSocket) and batch (REST) modes.

When enableVoiceProfile is true (the default), each recognized transcript includes an acoustic VoiceProfile in SpeechData.metadata.voiceProfile.

Example

const sttInstance = new STT({ enableVoiceProfile: true });
session = new AgentSession({ stt: sttInstance, ... });

Hierarchy (view full)

Constructors

Properties

label: string = 'inworld.STT'

Accessors

  • get capabilities(): STTCapabilities
  • Returns this STT's capabilities

    Returns STTCapabilities

  • get model(): string
  • Get the model name/identifier for this STT instance.

    Returns string

    The model name if available, "unknown" otherwise.

    Remarks

    Plugins should override this property to provide their model information.

  • get provider(): string
  • Get the provider name for this STT instance.

    Returns string

    The provider name if available, "unknown" otherwise.

    Remarks

    Plugins should override this property to provide their provider information.

Methods

  • Receives an audio buffer and returns transcription in the form of a SpeechEvent

    Parameters

    Returns Promise<SpeechEvent>