Use “Transcribe audio to notes” in Recued. Transcribe a recorded audio file (meeting / call / voice memo / interview) with the local whisper tool, then summarize the transcript into a readable note with key points, steered by the focus setting.

How it works 14 steps

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

Process (14 steps)

◆ transcribed recued-core.whisper.audio.transcribe

Transcribe audio on whisper

skip: config.source is_empty

■ file_ref default

Apply default

■ has_file compare

Check if file ref has data

✦ summarize core.ai.summarize

AI generates a concise summary

skip: step.has_file not_equal true

■ defaults defaults

Apply defaults

■ 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 core.storage.file.persist

Persist storage file

skip: step.skip_write equal true

■ row_key replace

Replace text in keep cas ref

◆ stage_row core.storage.shared.write

Write storage shared

skip: step.skip_write equal true

■ staged not

Apply not

■ card to_summary

Format results as a summary card

▼

Output

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 = [object Object]

max length setting = 250

write mode setting = preview

staging prefix setting = media_transcripts_staging