Catalog search - Patchline

Patchline builds a user-scoped search view of your catalog so you can search by free-text query, mood, genre, ISRC, metadata, and natural-language description similarity where uploaded audio has been captioned. This powers Aria’s catalog tools and the dashboard search bar. All tiers can search. Sonic-similarity ranking improves with catalog size and runs across the full catalog regardless of tier.

How to search

Web dashboard

Sidebar → Catalog → search bar at top. Type any query:

"melancholy dreampop for late-night listening"
"tracks like 'Sleeper'"
"sad and slow"
"ISRC GBUM71029604"

Results rank by combined relevance: keyword match + sonic similarity + recency.

Via Aria

Via MCP

catalog_search is the semantic search — pass any text query, get ranked results. browse_catalog is the listing endpoint — paginate through your full catalog without a query.

What you can search by

Query type	Example	What it returns
Title	`"Sleeper"`	Tracks with that title
Artist	`"Mira"`	Tracks by that artist
ISRC	`GBUM71029604`	The single matching track
Genre / mood tags	`"dreampop"`, `"melancholy"`	Tracks tagged with those
Natural-language vibe	`"slow sad ballad"`, `"late-night"`	Tracks whose AI caption matches the feel
Sonic similarity	`"like [track ID]"`	Tracks with similar audio to a reference track

The semantic layer means natural language works — “slow sad ballads for late night” returns the right tracks even if those exact words aren’t in any tag.

How search works

Catalog metadata is normalized on every catalog write.
Sonic features from sonic analysis ride alongside title, artist, ISRC, release date, and platform metadata.
Similarity features are available for tracks with completed audio analysis.
Results are scoped to your workspace and ranked by field match, freshness, audio similarity, and requested filters.

When you query, Patchline returns relevance-ranked results and merges in fresh presentation metadata before rendering.

Examples

Find a specific track by ISRC

You: GBUM71029604
Aria: That's "Bohemian Rhapsody" by Queen. Already in your catalog
      (imported 2026-04-12). Want full intel or just the audio features?

Find tracks for a playlist

You: I'm building a chill playlist — find me 10 tracks in my catalog
     that fit
Aria: 10 best fits (mellow, acoustic-leaning, slow):

  1. Sleeper (Mira) — melancholy dreampop, acoustic, low energy
  2. Long Way (Tessa) — drifting indie folk, soft vocals
  3. Velvet (Velvet Bird) — slow shoegaze, reverb-heavy
  4. ...

  Want me to make a smart link with these 10?

Find similar tracks

You: Find tracks in my catalog that sound like 'Late Bloom'
Aria: Top 5 by sonic similarity (cosine 0.7+):

  1. Late Bloom (the query track itself, 1.00)
  2. Bright Drop (Cleo Bell) — 0.81
  3. Soft Rain (Tessa) — 0.79
  4. ...

Browse without a query

You: List my catalog
Aria: 47 tracks total. Showing first 10:
  [paginated list with title, artist, metadata, caption snippet if available, last activity]

  Want to filter? "all dreampop", "tracks added this month", etc.

Limitations

Search is only as good as the indexed data. Tracks without completed sonic analysis won’t match audio-feature queries.
Similarity is catalog-only. “Find similar tracks” works within your own catalog.
Index lag is ~30 seconds. A freshly imported track is searchable within ~30 seconds of import completing.

Pricing

Plans, AI credits, and limits live on the pricing page — we keep them there so they’re always current.

Catalog import — what goes into the index
Catalog upload — file path
AI-discoverable tracks — the captions search ranks against
Playlists — match tracks to playlist targets

FAQ

Can I search across other users' catalogs?

No. Search is scoped to your Patchline workspace. Enterprise customers with multi-user workspace access search the shared workspace catalog.

Why didn't my just-imported track show up?

Search can have a ~30 second lag after import. Wait a moment and refresh. If still missing after 5 minutes, the import may have failed — check the catalog UI for an error state.

How are similar-track results ranked?

Patchline compares audio-similarity features from completed sonic analysis and filters out weak matches. Metadata, genre, and audience context can also affect the ranking.

Can I save searches?

Saved searches / smart playlists are on the roadmap. v1 you re-run the query.

​How to search

​Web dashboard

​Via Aria

​Via MCP

​What you can search by

​How search works

​Examples

​Find a specific track by ISRC

​Find tracks for a playlist

​Find similar tracks

​Browse without a query

​Limitations

​Pricing

​Related pages

​FAQ