Whisper STT Node
| Number of inputs | 1 |
| Number of outputs | 0 |
Configuration​
initializeModel​
Type: Bool
Indicates whether the model should be initialized when the node is created.
useGPU​
Type: Bool
Specifies whether to utilize GPU acceleration for faster processing.
Values​
Inherits values from its parent, SingleBusAudioSinkNode.
Actions​
Inherits actions from its parent, SingleBusAudioSinkNode.
loadModel​
Loads the specified whisper model.
Parameters​
| Name | Type | Description |
|---|---|---|
| modelPath | String | Path of the model to load. |
| useGPU | Bool | Whether to use GPU acceleration. |
transcribe​
Starts speech transcription process.
Parameters​
| Name | Type | Description |
|---|---|---|
| start | Int | Start of audio data that will be transcribed. |
| end | Int | End of audio data that will be transcribed. |
Events​
Inherits events from its parent, SingleBusAudioSinkNode.
transcription​
Emitted when text is transcribed.
Data​
| Name | Type | Description |
|---|---|---|
| text | String | The text that was transcribed. |