Whisper - Transcribe Audio with API
Overview
This Template takes in a audio file and transcribes it to a text file.
Variables
Name | Reference | Type | Required | Default | Options | Description |
|---|---|---|---|---|---|---|
API Key | WHISPER_API_KEY | Password | ✅ | - | - | API Key from OpenAI |
File to Transcribe | WHISPER_FILE | Alphanumeric | ✅ | - | - | The filename you wish to transcribe |
Transcription File Name | WHISPER_DESTINATION_FILE_NAME | Alphanumeric | ✅ |
| - | File name of transcription |
Language | WHISPER_LANGUAGE | Alphanumeric | ✅ |
| - | Language of the audio file. Should be in ISO-639-1 format. |
YAML
Below is the YAML template for this Template and can be used in the Fleet YAML Editor.
CODE
source:
blueprint: Whisper - Transcribe Audio with API
inputs:
WHISPER_API_KEY: null ## REQUIRED
WHISPER_FILE: null ## REQUIRED
WHISPER_DESTINATION_FILE_NAME: transcription.txt ## REQUIRED
WHISPER_LANGUAGE: en ## REQUIRED
type: BLUEPRINT
guardrails:
retry_count: 1
retry_wait: 0h0m0s
runtime_cutoff: 1h0m0s
exclude_exit_code_ranges:
- '0'