Transcribe media watch (Google Drive folder)
Use “Transcribe media watch (Google Drive folder)” in Recued. Watch a Google Drive folder for new audio or video recordings and stage a transcript + summary note for each.
How it works
Inspect the data fetches, transforms, gates, and output this recipe runs.
Process (43 steps)
listing
recued-core.gdrive.file.list
List file on gdrive
skip: config.folder_id is_empty
files
default
Apply default
candidates
filter
Filter by condition
seen
core.storage.shared.list
List storage shared
seen_entries
default
Apply default
is_stage_mode
compare
Check if setting write mode equals stage
terminal_entries
filter
Filter by condition
all_seen_ids
pluck
Extract value.file_id from each item
terminal_ids
pluck
Extract value.file_id from each item
blocked_ids
ternary
Apply ternary
unseen
filter
Filter by condition
unseen_count
count
Count items in unseen
processed_count
count
Count items in seen entries
pick
find
Find first match in
has_pick
compare
Check if pick exists
defaults
defaults
Apply defaults
is_video
compare
Check if mime contains video/
download
recued-core.gdrive.file.download
Download file on gdrive
skip: step.is_new not_equal true
download_ref
default
Apply default
do_extract
all
Check if all conditions are true
audio
recued-core.ffmpeg.media.extract_audio
Extract audio media on ffmpeg
skip: step.do_extract not_equal true
extracted_audio_ref
default
Apply default
audio_source
ternary
Apply ternary
has_audio_source
compare
Check if audio source has data
transcribed
recued-core.whisper.audio.transcribe
Transcribe audio on whisper
skip: step.has_audio_source not_equal true
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_2
defaults
Apply defaults
key_points_count
count
Count items in key points
key_points_text
join
Join items with "
"
media_kind
ternary
Apply ternary
now
date_add
Add 0 days to
skip_write
any
Check if any of the conditions are true
skip_keep_audio
any
Check if any of the conditions are true
keep_audio
core.storage.file.persist
Persist storage file
skip: step.skip_keep_audio equal true
keep_transcript
core.storage.file.persist
Persist storage file
skip: step.skip_write equal true
stage_row
core.storage.shared.write
Write storage shared
skip: step.skip_write equal true
staged
not
Apply not
marker_state
ternary
Apply ternary
processed
all
Check if all conditions are true
seen_write
core.storage.shared.write
Write storage shared
skip: step.processed not_equal true
card
to_summary
Format results as a summary card
▼
Output
summary
card
Settings
Configurable at install. Defaults shown — change them anytime in Recued.
focus
setting
=
key decisions, action items, and open questions
folder id
setting
=
max length
setting
=
250
write mode
setting
=
preview
staging prefix
setting
=
media_transcripts_staging
Uses (8 operations)
Pack operation
List file on gdrive
recued-core.gdrive.file.list
Shared store
List storage shared
core.storage.shared.list
Pack operation
Download file on gdrive
recued-core.gdrive.file.download
Pack operation
Extract audio media on ffmpeg
recued-core.ffmpeg.media.extract_audio
Pack operation
Transcribe audio on whisper
recued-core.whisper.audio.transcribe
AI models
AI generates a concise summary
core.ai.summarize
Files
Persist storage file
core.storage.file.persist
Shared store
Write storage shared
core.storage.shared.write
Trust & control
What installing this recipe would let it do. Recued grants these permissions at install — review them there before approving.
What it's allowed to do
Read
Shared store
core.storage.shared.list
read-only
Read
AI models
core.ai.summarize
read-only
Write
Files
core.storage.file.persist
external change
Write
Shared store
core.storage.shared.write
external change
4 more aren't listed here. You'll see them at install.