Skip to main content

๐Ÿค– Google Sheets



Before using the extension, you need to set your API key. Select in the toolbar Muse > Settings > Register API Key. Enter your API key and click on the submit button.

You will find your API key in Account > API Keys.

If you don't have an API key, subscribe to

You can load some examples using the Load an example sheet button from the Muse tab.

The layout to follow is:

This AI-powered Google Sheets extension is15nucleusthe result of hours of testing, a hefty price tag and a staff full
The AI algorithms behind Muse are20"."generally well-known and recognized leaders in their respective fields.

Having the prompt keyword (any case) in the upper-left corner of the selection is mandatory.


You can add as many columns you want between the prompt column and the completion column. Leaving a cell empty will skip the parameter for the matching prompt.

Selecting a model

You can change the model used by the current sheet in Muse > Settings > Select model.

Models are available in the Models tab.

Complete cellsโ€‹

Available parametersโ€‹

  • n_tokens number 20

    Number of tokens to generate. This can be overridden by a list of stop_words, which will cause generation to halt when a word in such list is encountered.

  • best_of number null

    Among n_completions, only return the best_of ones. Completions are selected according to how likely they are, summing the log-likelihood over all tokens generated.


    See the sampling entry for more details.

  • mode (greedy, topk, nucleus, typical) nucleus

    How the model will decide which token to select at each step.

    • Greedy: the model will always select the most likely token. This generation mode is deterministic and only suited for applications in which there is a ground truth the model is expected to return (e.g. question answering).
    • Top K: the model will only consider the k most likely tokens. For some models, in particular lyra-fr, this mode is a very good alternative to nucleus sampling.
    • Nucleus: the model will only consider the most likely tokens with total probability mass p. We recommend this setting for most applications.
    • Typical: the model will discard high probability tokens with low expected information content.
  • temperature number 1.0 โš ๏ธ only in topk/nucleus mode

    How risky will the model be in its choice of tokens. A temperature of 0 corresponds to greedy sampling. we recommend a value around 1 for most creative applications, and closer to 0 when a ground truth exists.

  • p number 0.9 โš ๏ธ only in nucleus mode

    Total probability mass of the most likely tokens considered when sampling in nucleus mode.

  • k number 5 โš ๏ธ only in topk mode

    Number of most likely tokens considered when sampling in top-k mode.


  • biases Record<string, number> null

    Google Sheets format

    You must surround each word with double quotes, add a semicolon and the weight you want to apply to this word. You need to separate them with commas.

    Like: "positive": 2, "negative": -50, "cinema": 4.

    Bias the provided words to appear more or less often in the generated text. Values should be comprised between -100 and +100, with negative values making words less likely to occur. Extreme values such as -100 will completely forbid a word, while values between 1-5 will make the word more likely to appear. We recommend playing around to find a good fit for your use case.

    ๐Ÿ’ก Avoiding repetitions

    When generating longer samples with biases, the model may repeat positively biased words too often. Combine this option with presence_penalty and frequency_penalty to achieve best results. If you generate a first completion, and then use it as a prompt for a new completion, you probably want to turn off the word bias encouraging a certain word once it has been produced to avoid too much repetition.

  • presence_penalty number 0.0

    How strongly should tokens be prevented from appearing again. This is a one-off penalty: tokens will be penalized after their first appearance, but not more if they appear repetitively. Use frequency_penalty if that's what you want instead. Use values between 0 and 1. Values closer to 1 encourage variation of the topics generated.

  • frequency_penalty number 0.0

    How strongly should tokens be prevented from appearing again if they have appeared repetitively. Contrary to presence_penalty, this penalty scales with how often the token already occurs. Use values between 0 and 1. Values closer to 1 discourage repetition, especially useful in combination with biases.

  • stop_words List<string> null

    Encountering any of these words will halt generation immediately.

    Google Sheets format

    You must surround each word with double quotes and separate them with commas.

    Like: "end", ".", ";".


  • concat_prompt boolean false

    The original prompt will be concatenated with the generated text in the returned response.

  • seed number null

    Make sampling deterministic by setting a seed used for random number generation. Useful for strictly reproducing Create calls.


  • skill string null

    Specify a ๐Ÿคน Skill to use to perform a specific task or to tailor the generated text.