Extract summaries from newly shared videos
When a new video is shared in Spotify, automatically send the transcript to Deepgram to generate key bullet points and action items.
Google for Startups AcceleratorHow Knit builds this workflow
The Agent researches both APIs and wires the trigger on one side to the action on the other — no pre-built connector required. Here is the vocabulary it has to work with.
Deepgram Explore Deepgram →
TriggersFires when Deepgram generates a response to a prompt.
Fires when a request to Deepgram errors or times out.
Fires when a fine-tuning job in Deepgram finishes.
Sends a prompt to Deepgram and returns the model's response.
Uses Deepgram to summarize a block of text.
Uses Deepgram to classify or extract structured data from text.
Spotify Explore Spotify →
TriggersFires when a new video is recorded or shared in Spotify.
Fires when someone comments on a video in Spotify.
Fires when a new video recording or comment is added in Spotify.
Sends a video message via Spotify.
Shares a video link from Spotify.
Posts a video from Spotify to a channel.
More Deepgram + Spotify workflows
See all Deepgram + Spotify integrations → · Browse the full workflow library →
Enterprise-grade security
Common questions
Can Knit build “Extract summaries from newly shared videos” between Deepgram and Spotify?
Yes — describe it in the box above and Knit's Integrations Agent researches Deepgram and Spotify's public API docs (or your own uploaded docs) and builds a working workflow, whether or not either app already has a pre-built connector.
How long does it take to build?
Minutes to a first working version, not weeks — you test it against real data before it goes anywhere near production.
What's the most common AI Models + Video & Communication automation?
Having Deepgram summarize a call transcript from Spotify into key points and action items right after the call ends.
Does this need Spotify to already generate a transcript?
If Spotify exposes a transcript, Deepgram uses that directly; if not, the Agent can work from the recording itself depending on what's available.