Deepgram audio intelligence brief
Use “Deepgram audio intelligence brief” in Recued. Synchronous Deepgram audio intelligence workflow.
How it works
Inspect the data fetches, transforms, gates, and output this recipe runs.
Process (9 steps)
normalized_url
trim
Trim whitespace from setting audio url
transcription
recued-core.deepgram.transcription.create
Create transcription on deepgram
defaults
defaults
Apply defaults
utterances
slice
Take a subset of
channel_count
count
Count items in channels
utterance_count
count
Count items in utterances raw
summarize
core.ai.summarize
AI generates a concise summary
utterance_table
to_table
Format results as a data table
card
to_summary
Format results as a summary card
▼
Output
summary
card
table
utterance_table
Settings
Configurable at install. Defaults shown — change them anytime in Recued.
focus
setting
=
Summarize the transcript, Deepgram summary, sentiment, topics, intents, speaker turns, quality signals, and follow-up actions. Use only the Deepgram response.
model
setting
=
nova-3
topics
setting
=
true
intents
setting
=
false
language
setting
=
en
audio url
setting
=
row limit
setting
=
20
sentiment
setting
=
true
summarize
setting
=
v2
max length
setting
=
900
Uses (2 operations)
Pack operation
Create transcription on deepgram
recued-core.deepgram.transcription.create
AI models
AI generates a concise summary
core.ai.summarize
Trust & control
What installing this recipe would let it do. Recued grants these permissions at install — review them there before approving.
Permissions it requires
Declared by the recipe — Recued grants these at install, where you review them before approving.What it's allowed to do
Read
AI models
core.ai.summarize
read-only
1 more isn't listed here. You'll see it at install.