The text to analyze against moderation categories. Read more.

File uploads are limited to 25 MB and the following file types: mp3, mp4, mpeg, mpga, m4a, wav, and webm.

You may use a prompt to improve the quality of the translation. Including specific keywords or acronyms in the audio can reduce misspellings. The prompt should be in English.

Defaults to Text.

Data sent to OpenAI through this Zap is via API. Under OpenAI's API data usage policy, OpenAI will not use API-submitted data to train or improve their models unless you explicitly decide to share your data with them for that purpose (such as by opting in). For more information, please review OpenAI's article about when/how data may be used to improve model performance.

We recommend "text-davinci-003" for most tasks. Note: Looking for "gpt-4" or "gpt-3.5-turbo" models? Please use the ChatGPT app instead. Learn More.

Writing a good prompt is important. Start by creating a clear goal & ask a specific question. Make sure the prompt is well structured & provides enough context for the OpenAI to generate a useful response. Learn More.

Higher values mean the model will take more risks. Try 0.9 for more creative applications, and 0 for ones with a well-defined answer.

We generally recommend altering this or Top P but not both.

The maximum number of tokens for the completion. If you leave this field empty, we will attempt to auto-calculate this so you avoid going over your model's context length limit. If we can't auto-calculate for your particular model, we will default to 256 tokens.

Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.

An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.

Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.

Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.

A string that you want to search for. EG: "large animal".

The list of documents to search through. EG: "mouse", "cat", "buffalo", and "blue whale".

Note: we handle the embeddings for you, by computing a cosine difference between this query and each of the documents. Read more.

File uploads are limited to 25 MB and the following file types: mp3, mp4, mpeg, mpga, m4a, wav, and webm.

You may use a prompt to improve the quality of the transcription. Including specific keywords or acronyms in the audio can reduce misspellings. Including punctuation in the prompt can help ensure the transcript has punctuation. The prompt should match the audio language.

Defaults to Text.

It is best to provide the language in ISO 639-1 format. Defaults to en (English).

Use a detailed description for DALL-E to generate into an image. EG: An impressionist oil painting of sunflowers in a purple vase. Read more.

Number of image variations (1 - 10).

Select the size of image.

API docs for OpenAI (GPT-3, DALL·E, Whisper) are located here https://beta.openai.com/docs/introduction

Requests can only be made to domains associated by this application.

These params will be URL-encoded and appended to the URL when making the request.

Authentication headers are included automatically

Zapier will apply these optional headers and values to the request in addition to any headers created as part of the authentication mechanism.

Zapier will pass this along raw. If you would like to provide complex JSON, try a "Code by Zapier" step to build the structure and pass it along here. For example, {"foo": "bar"} is perfectly valid.