Skip to main content

Documentation Index

Fetch the complete documentation index at: https://dev.docs.inworld.ai/llms.txt

Use this file to discover all available pages before exploring further.

Overview > Inworld Node > Inworld Node STT Class: UInworldNode_STT | Inherits from: UInworldNode A node that converts audio input to text using Speech-to-Text functionality. This node takes audio input and processes it through a Speech-to-Text service to generate text output. It inherits from TypedNode with Text as output and Audio as input. Inworld Node STT Input Types:
  • FInworldData_Audio OR FInworldData_DataStream_AudioChunk (Audio data to convert to text)
Output Types:
  • FInworldData_Text

​
Execution Config

The STT node exposes an ExecutionConfig property (FInworldSTTNodeExecutionConfig) that controls whether it runs in batch or streaming mode.
PropertyTypeDefaultDescription
bStreamedboolfalseWhen true, the node uses a Streaming STT primitive and processes audio incrementally in real-time. When false, it sends a complete audio clip to a batch STT primitive.
STTComponentIdFString"Default"The STT Creation Config key to use. Only visible when bStreamed is false.
StreamingSTTComponentIdFString"Default"The Streaming STT Creation Config key to use. Only visible when bStreamed is true.
Set bStreamed = true when the node receives a FInworldData_DataStream_AudioChunk input (live microphone audio). Use the default false for complete pre-recorded audio clips (FInworldData_Audio).