Speech To Text
This module is adept at transcribing audio data into text, offering outputs in both plain text and JSON formats.
Inputs
Inputs divide into public and private. Public input is for user's interaction with block. Private input is for communication between block and block. You can't use these inputs directly
| name | type | accessibility |
|---|---|---|
| input | audio | Private |
Fields
| name | description | details |
|---|---|---|
| Inputs | The inputs to the block. | N/A |
| Name | The name of the block. Can only contain letters, numbers, and underscores. Cannot include spaces. | N/A |
| Stop after (ms) | The temperature specifies the maximum duration (in ms.) for an operation to complete before the system terminates it due to inactivity or delay. | Default: 10000 |
| Model | Model allows you to supply a model to use to process submitted audio. | N/A |
| Language | Language of the transcription. | N/A |
| API key | Deepgram API key | N/A |