Acoustic Attributes Overview

An acoustic attribute is an estimated subjective quality of a track. It is modeled through learning and is given as a single floating point number ranging from 0.0 to 1.0. The Echo Nest derives the attributes of a song from the audio tracks that comprise it. Songs can be sorted by any of these axes, or the attributes can be used as filters for constructing custom playlists.

Some of our currently available acoustic attributes are described below.

For a detailed description of how to interpret the analyzer output see the Analyze Documentation.

Danceability

Describes how suitable a track is for dancing using a number of musical elements (the more suitable for dancing, the closer to 1.0 the value). The combination of musical elements that best characterize danceability include tempo, rhythm stability, beat strength, and overall regularity.

Energy

Represents a perceptual measure of intensity and powerful activity released throughout the track. Typical energetic tracks feel fast, loud, and noisy. For example, death metal has high energy, while a Bach prelude scores low on the scale. Perceptual features contributing to this attribute include dynamic range, perceived loudness, timbre, onset rate, and general entropy.

Speechiness

Detects the presence of spoken words in a track. The more exclusively speech-like the recording (e.g. talk show, audio book, poetry), the closer to 1.0 the attribute value. Values above 0.66 describe tracks that are probably made entirely of spoken words. Values between 0.33 and 0.66 describe tracks that may contain both music and speech, either in sections or layered, including such cases as rap music. Values below 0.33 most likely represent music and other non-speech-like tracks.

Liveness

Detects the presence of an audience in the recording. The more confident that the track is live, the closer to 1.0 the attribute value. Due to the relatively small population of live tracks in the overall domain, the threshold for detecting liveness is higher than for speechiness. A value above 0.8 provides strong likelihood that the track is live. Values between 0.6 and 0.8 describe tracks that may or may not be live or contain simulated audience sounds at the beginning or end. Values below 0.6 most likely represent studio recordings.

Acousticness

Represents the likelihood a recording was created by solely acoustic means such as voice and acoustic instruments as opposed to electronically such as with synthesized, amplified, or effected instruments. Tracks with low acousticness include electric guitars, distortion, synthesizers, auto-tuned vocals, and drum machines, whereas songs with orchestral instruments, acoustic guitars, unaltered voice, and natural drum kits will have acousticness values closer to 1.0.

Valence

Describes the musical positiveness conveyed by a track. Tracks with high valence sound more positive (e.g., happy, cheerful, euphoric), while tracks with low valence sound more negative (e.g. sad, depressed, angry). This attribute in combination with energy is a strong indicator of acoustic mood, the general emotional qualities that may characterize the track's acoustics. Note that in the case of vocal music, lyrics may differ semantically from the perceived acoustic mood.