Make a karaoke track (remove vocals, change key and tempo)
Make a karaoke track for singing practice in one step. Remove the vocals, move the key up or down to suit your voice, set a comfortable tempo and export a single file. You can also keep the vocals quiet as a guide so you can follow the melody.
The first run downloads an AI model (about 90 MB); later runs use the copy stored in your browser. Nothing but the model is transferred and your files are never uploaded.
Settings
How to use
- 1
Add a song
Drop the song you want to turn into karaoke. Video files work too.
- 2
Set vocals, key and tempo
Remove the vocals completely or keep them quiet as a guide. Change the key by ±12 semitones and the tempo from 50 to 150%.
- 3
Run and save
Vocal removal, key change and tempo change are done in one pass and saved as a single file. The first run downloads the AI model (about 90 MB).
How the key and tempo are changed
The vocals are separated and removed by AI (HTDemucs). The key can move up to ±12 semitones (one octave) without changing the tempo, and the tempo can change from 50 to 150% without changing the key. Both use WSOLA, which cuts the waveform into short segments and overlaps them again.
The further you move the key (roughly ±5 semitones or more), the less natural the sound becomes. If the original key is far from your range, consider singing an octave up or down. In Chrome or Edge on a computer it runs on the GPU (WebGPU); on the laptop we tested (integrated GPU) a 4-minute song took about 1 minute. On iPhone, iPad and Safari it runs on the CPU and takes longer: about 7 minutes for a 4-minute song on an iPhone 15 Pro Max.
Frequently asked questions
How far can I change the key? Does the tempo change?
The key moves up to ±12 semitones (one octave) without changing the tempo. The tempo can also be set separately from 50 to 150% without changing the key. The further you move the key (roughly ±5 semitones or more), the less natural the sound becomes.
Can I make a version with a guide vocal?
Yes. Choose “Keep quiet (-12 dB, guide vocal)” under “Vocals” to keep the vocals faintly audible so you can follow the melody. “Keep very quiet (-18 dB)” and “Keep a little (-6 dB)” are also available.
Can I make one on my phone?
Yes. No app is needed; just open this page in your browser. On iPhone and iPad it runs on the CPU, so a 4-minute song takes about 7 minutes. Keep the screen on and this page open while it runs. The song is never uploaded.
Can I publish videos using the track?
Publishing a track made from a commercial song requires permission from the rights holders. Keep it to personal use such as karaoke practice.
Help us improve the service
If a conversion fails, sending us the circumstances helps us track down the cause. Knowing which devices and formats fail most often, and how long processing takes, lets us revise the supported formats and fix the bugs behind them. If you don't mind, leaving this on is a real help.
What is sent
The tool you used and the settings you chose (output format, quality, etc.), your device specs (GPU, memory, core count), the input format with a rough size, how many files succeeded or failed and how long it took, and the error type and details when something fails.
What is never sent
The files themselves, file names, text, subtitles or prompts you add to a video, and IP addresses. The data goes only to this site's own server, never to a third-party service.