Azure Transcribe
Transcribes audio into subtitles using Azure's Speech service, optionally translating them into any number of other languages at the same time.
Component Configuration
| Option | Description | Required | Environment override |
|---|---|---|---|
id |
A unique identifier for the component instance |
✓ |
|
displayName |
The name shown in the Studio UI of this component |
✓ |
|
sourceLanguage |
Source language to transcribe (default: "en-US") |
✗ |
|
targetLanguages |
Languages to translate the subtitles into. Selecting any switches the component from transcription to translation: it then produces one subtitle track per language listed here and no original-language transcript. Leave empty to produce the source-language transcript only. (default: []) |
✗ |
|
azureKey |
Azure Speech key. Leave blank to use the AZURE_SPEECH_KEY environment variable. |
✗ |
|
azureRegion |
Azure Speech region short name, for example westeurope or uksouth (not the portal display name like "UK South"). Leave blank to use the AZURE_SPEECH_REGION environment variable. |
✗ |
|
dictation |
Recognise dictated punctuation ("comma", "new line") rather than transcribing it verbatim (default: false) |
✗ |
|
profanity |
What to do with profanity in the output |
✗ |
|
notes |
Additional notes about this component |
✗ |
Tags: