logo

audiotranscriptionopenai - Transcribe Audio with OpenAI

Version: 1.0.0
Credits: 10

Transcribes audio to text. Will be charged per minute.
Audiotranscriptionopenai is a service that transcribes audio files to text using OpenAI's language model. It's a paid service that charges per minute of audio transcribed.

To use audiotranscriptionopenai, provide the audio file in the MP3 format and other properties such as the prompt, sampling temperature, and language in the JSON format. The language input improves the accuracy and latency of the transcription process. You will be charged based on the duration of the audio file transcribed, and the result will be returned as a transcripted text with the duration of the process in minutes.

Example: Transcribing a 30-second audio file with a sampling temperature of 0.2, which makes the output more focused and deterministic.

file
Type
binary
The audio or video file to transcribe.
fileUrl
Type
url
The URL of an audio or video file to transcribe.
prompt
Type
string
An optional text to guide the model's style or continue a previous audio segment. The prompt should match the audio language.
Example:
1001fx is a nocode function set
temperature
Type
number
The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. Default is 0
Example:
0.2
language
Type
string
The language of the input audio. Supplying the input language in ISO-639-1 format will improve accuracy and latency. See https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes
Example:
DE
responseFormat
Type
string
The format of the transcript output. Defaults to json.
Possible values are: json, vtt
Example:
json

Available on

Postman
Make
Zapier
N8N
Airtable
SeaTable
Bubble
Power Automate
Workato
SAP Build