Transcribe a recorded video (screen recording / call recording / webinar): the local ffmpeg tool extracts the audio track, the local whisper tool transcribes it, and the transcript is summarized into a readable note with key points, steered by the focus variable. Content-isolated: media and transcript move as Gateway-gated file refs, never through step values. Preview-first: shows the note and writes nothing; set write_mode to stage to persist it (with audio and transcript pointers) into data.shared. Source: a local video path or a data.file ref (e.g. a Drive download).

How it works 19 steps

Inspect the data fetches, transforms, gates, and output this recipe runs.

Process (19 steps)

■ audio ?

skip: config.source is_empty

■ audio_ref default

Apply default

■ has_audio compare

Check if audio ref has data

■ transcribed ?

skip: step.has_audio not_equal true

■ file_ref default

Apply default

■ has_file compare

Check if file ref has data

■ summarize ?

skip: step.has_file not_equal true

■ summary default

Apply default

■ key_points default

Apply default

■ key_points_count count

Count items in key points

■ key_points_text join

Join items with " "

■ now date_add

Add 0 days to

■ skip_write any

Check if any of the conditions are true

■ keep_audio ?

skip: step.skip_write equal true

■ keep_transcript ?

skip: step.skip_write equal true

■ row_key replace

Replace text in keep transcript cas ref

■ stage_row ?

skip: step.skip_write equal true

■ staged not

Apply not

■ card to_summary

Format results as a summary card

Settings 6 configurable

Configurable at install. Defaults shown — change them anytime in Recued.

focus setting = key decisions, action items, and open questions

title setting =

source setting =

max length setting = 250

write mode setting = preview

staging prefix setting = media_transcripts_staging