The moment it happens
Build a Spotify playlist from a mood you describe
You send an idea like "rainy Sunday jazz" and get an email with a link to a new 20-song playlist.
- Runs
- The moment it happens
- Apps
- Spotify
- AI
- Yes, uses the built-in AI allowance
- Access
- playlist-modify-private/public
Send this to your assistant
Create a ClickRuntime automation: give me a link where I can send a playlist idea. Have AI pick 20 songs that fit it, find them on Spotify, create a private playlist and email me the link.
First time? Adding ClickRuntime to your assistant takes about two minutes.
Why use it
Why teams use this automation
You want music for a specific moment: a rainy Sunday cooking session, a 90-minute focus block, a wedding cocktail hour, a run at a steady 160 beats per minute. Spotify's search finds individual songs, and editorial playlists are generic. Building the right one yourself means thinking of fifty tracks, searching for each, checking that it is the right version and adding them one at a time. Most people give up after ten songs and settle for something close.
You send a short description, either from a form, a shortcut on your phone or any tool that can call a URL. ClickRuntime's built-in AI proposes a list of tracks and artists that fit it, searches for each on Spotify, creates a new playlist in your account, adds the tracks that were found and emails you the link to open.
DJs planning sets, event hosts, fitness instructors and anyone who is tired of making playlists by hand will get the most from it.
What you get out of it
Playlists exist in a minute, not an evening
A mood or a theme becomes a ready playlist before the thought has passed. Event hosts and instructors can prepare a different list for each class or occasion without the usual time spent searching song by song.
Descriptions can be as specific as you like
Asking for upbeat 80s synth-pop with no ballads, or quiet piano for studying, gives a result shaped by your words. Every request produces a playlist matched to that situation instead of a generic one.
New artists are introduced alongside favorites
The AI draws on a broad knowledge of music, so lists often include songs you did not think to search for. That is one of the best ways to discover tracks that fit a mood.
Real Spotify tracks are used
Each suggestion is searched on Spotify, and only those found are added, so you do not end up with invented songs. The playlist works immediately in the app on your phone or speakers.
Sharing is trivial
The link arrives by email, so you can pass it to a guest, a colleague or a class straight away. Everyone hears the same list, and it stays in your account to reuse next time.
How it works
What happens, step by step
When you send an idea like "rainy Sunday jazz" to your automation's link, ClickRuntime starts straight away.
AI suggests around 20 songs and artists that fit the mood.
ClickRuntime finds each song on Spotify and adds the ones it finds to a new playlist named after your idea.
You get an email with the playlist link and how many songs made it in.
Before it runs live
- Connect Spotify
- Paste your automation's link into the other app's webhook settings
What you get
Build your own
Need it to work differently?
Your own rules
Conditions, thresholds, filters and exceptions, written the way you'd explain them to a colleague.
Any number of apps
One automation can read from one app and update several others. Over 248 apps are ready, and anything with an API works too.
AI where it helps
Summaries, classification, extraction and drafts use ClickRuntime's built-in AI, with no extra key.
On a schedule or on each event
Runs as often as every 5 minutes, or the moment an app sends an event, and keeps track of what it already handled.
Changes you can ask for
- Act only on the items that match your own rules, and skip the rest
- Change what the AI looks for, or how it writes the result
- Add another app, for example also send it to Slack
- Combine it with other Spotify steps into one automation
Under the hood
The code that runs this automation
from clickruntime import on_event, credentials, http, ai, notify
API = "https://api.spotify.com/v1"
@on_event
def handle(event):
idea = (event.json or {}).get("idea", "")
h = {"Authorization": f"Bearer {credentials.connection('spotify', 'personal')}"}
picks = ai.generate(f"Suggest 20 real songs for a playlist: {idea}",
json_schema={"type": "object", "properties": {"songs": {"type": "array", "items": {
"type": "object", "properties": {"title": {"type": "string"}, "artist": {"type": "string"}}}}}},
max_output_tokens=800).json["songs"]
uris = []
for s in picks:
found = http.get(f"{API}/search", headers=h, params={
"q": f"track:{s['title']} artist:{s['artist']}", "type": "track", "limit": 1}).json()
items = found["tracks"]["items"]
if items:
uris.append(items[0]["uri"])
playlist = http.post(f"{API}/me/playlists", headers=h,
json={"name": idea[:80], "public": False}).json()
http.post(f"{API}/playlists/{playlist['id']}/tracks", headers=h, json={"uris": uris})
notify.email_me(f"Your playlist: {idea[:60]}", f"{len(uris)} songs\n{playlist['external_urls']['spotify']}")
return {"tracks": len(uris)}FAQ
Common questions
Does it need a Spotify Premium account?
What if a suggested song cannot be found on Spotify?
How many songs does the playlist contain?
What permissions does it need?
Does it need AI?
How many runs does it use?
Can I change how it works?
Related
You might also like
Queue, skip or pause Spotify from a link
Calling a link adds a track to your queue, skips to the next song or pauses playback.
See how it worksSave Discover Weekly to a permanent playlist each Monday
Each week's Discover Weekly tracks land in an archive playlist, with no duplicates.
See how it worksCollect each month's liked songs in their own playlist
Songs you like go into a playlist named for the month, created when the month starts.
See how it worksKeep exploring
Set up “Build a Spotify playlist from a mood you describe” from your assistant
Copy the prompt above, or connect your assistant first. Free plan, no credit card.