LeMUR

Summarize a transcript using LeMUR

POST
Custom Summary allows you to distill a piece of audio into a few impactful sentences. You can give the model context to obtain more targeted results while outputting the results in a variety of formats described in human language.

Request

This endpoint expects an object.
answer_format
stringOptional
How you want the summary to be returned. This can be any text. Examples: "TLDR", "bullet points"
context
unionOptional
Context to provide the model. This can be a string or a free-form JSON value.
final_model
enumOptional
The model that is used for the final prompt after compression is performed.
input_text
stringOptional

Custom formatted transcript data. Maximum size is the context limit of the selected model, which defaults to 100000. Use either transcript_ids or input_text as input into LeMUR.

max_output_size
integerOptional
Max output size in tokens, up to 4000
temperature
doubleOptional
The temperature to use for the model. Higher values result in answers that are more creative, lower values are more conservative. Can be any value between 0.0 and 1.0 inclusive.
transcript_ids
list of stringsOptional

A list of completed transcripts with text. Up to a maximum of 100 files or 100 hours, whichever is lower. Use either transcript_ids or input_text as input into LeMUR.

Response

This endpoint returns an object
request_id
string
The ID of the LeMUR request
response
string
The response generated by LeMUR.
usage
object
The usage numbers for the LeMUR request