OpenAITranscribe - ChatGPT & OpenAI

← ChatGPT & OpenAI Add-On Übersicht

This Step automatically transcribes text from any given spoken audio. Approximately 92 languages are supported. The automatic translation to english is also possible.

Inputs

Das sind die Optionen, mit denen man den Step konfigurieren kann.

Name	Datentyp	Beschreibung	Pflichtfeld	Werte
account	ACCOUNT	Your OpenAI Account	Ja
mode	STRING	Select to either transcribe audio in its original language or automatically translate output into english.	Ja	transcription translation
transcriptionModels	STRING	The models to be used for the transcription API. The translations route always uses the whisper-1 model.	Nein	whisper-1 gpt-4o-transcribe gpt-4o-mini-transcribe
format	STRING	The format of the transcript output.	Ja	txt (Text) srt (SubRip Subtitle) vtt (Video Text Tracks)
prompt	STRING	You can use a prompt to improve the quality of the transcripts generated by the Whisper API. The model will try to match the style of the prompt, so it will be more likely to use capitalization and punctuation if the prompt does too. However, the current prompting system is much more limited than our other language models and only provides limited control over the generated audio.	Nein
audio	FILE	The audio file. Support audio formats are: mp3, mp4, mpeg, mpga, m4a, wav, and webm	Ja

Outputs

Das sind die Ergebnisse des Steps, die von nachfolgenden Steps, nach der Ausführung verwendet werden können.

Name

Datentyp

Beschreibung

Pflichtfeld

Werte

response

SPREADSHEET

The Response Spreadsheet

Folgende Felder sind im Output enthalten :

Feld	Datentyp	Pflichtfeld
file	SINGLE	Nein
format	SINGLE	Nein
text	SINGLE	Nein

text

STRING

The response as string.

file

FILE

The response as file.

subtitles

SPREADSHEET

If SRT or VTT is selected, this spreadsheet outputs timecodes and corresponding texts.

Folgende Felder sind im Output enthalten :

Feld	Datentyp	Pflichtfeld
line	SINGLE	Nein
from	SINGLE	Nein
to	SINGLE	Nein
text	SINGLE	Nein