Find Similar-Sounding Tracks
find_similar_tracksTracks that SOUND like one seed track or a set of up to 10, optionally restricted by tempo, key, genre, year, chart or audio-feature ranges — e.g. "like these three, but 120-128 BPM in 8A or its neighbours": seed_tracks=[...], min={"tempo": 120}, max={"tempo": 128}, key="8A", harmonic=true.
Ranked mainly on a PANNs audio embedding (how the recording sounds) blended with an
audio-feature similarity. Results are one per recording, with `score`, `genre_relation`
to the seed and, with several seeds, `matched_seed`. With filters, results are the
closest-sounding tracks that pass every filter, and `filters` reports what was applied
and how many catalog tracks each one removed (`dropped_by`) — loosen the largest if the
list is short. Use get_recommendations instead when you want preferred target values
(target energy etc.) rather than hard filters. Costs 1 quota unit.
PANNs (Kong et al., 2020) is used under CC BY 4.0.
Tool call template
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "find_similar_tracks"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| key | No | Filter — comma list of keys: Camelot ('8A'), Open Key ('1m') or names ('A minor'). | |
| max | No | Filter — HARD upper bounds, e.g. {'tempo': 128}. Same attributes as `min`. | |
| min | No | Filter — HARD lower bounds on the results, e.g. {'tempo': 120, 'energy': 0.6}. Attributes: acousticness, danceability, duration_ms, energy, loudness, tempo, valence. | |
| mode | No | Filter — 'major' or 'minor' only. | |
| blend | No | With several seeds: 'all' (default) = sounds like the set as a whole, best when the seeds share a style; 'any' = every seed gets its own neighbours, interleaved — use it when the seeds are from different genres, where 'all' would average them into tracks that sound like none of them. | all |
| genre | No | Filter — comma list of catalog genre names, e.g. 'house'. Unknown names in a list are skipped and listed in filters.ignored with close matches; only a list where every name is unknown is rejected. | |
| limit | No | Results to return (default 10). | |
| charted | No | Filter — true = only tracks with a known chart placement. | |
| explicit | No | Filter — true = explicit only, false = non-explicit only. | |
| harmonic | No | Widen each key to its harmonically compatible keys. | |
| max_year | No | Filter — latest release year. | |
| min_year | No | Filter — earliest release year. | |
| track_id | No | One seed: a catalog itunes_track_id (from search_catalog or get_audio_features). Omit when using seed_tracks / seed_isrcs. | |
| seed_isrcs | No | Several seeds by ISRC (up to 10 together with seed_tracks). | |
| cross_genre | No | Genre lane: 'auto' (default, keep results mixable with the seed's genre), 'allow' (genre-blind), 'strict' (seed's genre family only). | auto |
| seed_tracks | No | Several seeds: catalog itunes_track_ids (up to 10 together with seed_isrcs). | |
| tempo_match | No | With a tempo bound: 'exact' (default) or 'half_double' (also match double/half the range). | exact |
| min_chart_peak | No | Filter — best chart position required, as chart_peak (100 = a number one). | |
| include_subgenres | No | Also match every subgenre of a top-level genre. | |
| exclude_same_artist | No | Drop other tracks by the seed artist(s). |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||