Why you can trust us

Engadget has been testing and reviewing consumer tech since 2004. Our stories may include affiliate links; if you buy something through a link, we may earn a commission. Read more about how we evaluate products.

Deezer can now identify songs that you hum

You can add the tracks it identifies straight to your playlist.


Deezer can now help you find songs that suddenly start playing in your head in the middle of the night. The music streaming service has upgraded its in-app SongCatcher feature so that it can now identify a track just by humming or even whistling parts of it. Once the service identifies a track, it will show you an information page with its title, artist and single/album cover where you can play the song, add it your playlist or queue and add it to your favorites.

The company says it's the only music streaming service with an in-app track recognition feature that includes humming and whistling, but it's worth noting that you can do the same within Google search. I tester Deezer's new feature and compared it with Google's and found that the latter is a bit better at recognizing my off-key humming. Google was even able to easily ID the more obscure parts of some Japanese pop songs.

For Deezer, I sometimes had to hum the more recognizable parts of a track, such as its chorus, even if they're enormous hits. I'm talking songs like Lady Gaga's Always Remember Us This Way, Ariana Grande's Thank U, Next and Lil Nas X's Industry Baby. If you're a subscriber, though, it's the more convenient option, seeing as you can directly add tracks to your playlists. To ID songs by humming, you simply have to go to Search, then tap on "What's this song" to launch SongCatcher and choose "Sing Now."

Maybe I was just extra out of tune while testing Deezer — nobody has ever called me a good singer. The good news is that the feature could become much better at identifying tracks over time. Alexandra Leloup, VP Core Product at the company, explained: "As we keep improving the algorithm, the feature will become faster and even more accurate when it comes to recognizing songs across our 90 million track library."