Split a song into 4 stems
With AI, in your browser
Stem Splitter
Choose your audio in MP3 or WAV
Your audio is processed on your device
Pick a card to see its tools
With AI, in your browser
Stem Splitter
TikTok Slowed · 80 %Slowed audio with reverb
Paste a video link and download its audio as MP3.
10 tools
Generate and transcribe speech, separate stems and clean up recordings with AI.
Generate Spanish or English speech and download the audio.
Transcribe audio locally and export text and subtitles.
Generate English speech using an authorized voice sample.
Transform a recording with voice effects.
Separate vocals and instrumental with a local model.
Separate vocals, drums, bass and other instruments.
Reduce stationary noise and hum in a recording.
Adjust the notes of an isolated voice to a scale.
Turn a hummed melody into a synthesized instrument.
Add a musical backing and pitch correction to your recording.
11 tools
Equalize, add reverb and create the viral sounds: nightcore, slowed, 8D…
8-band parametric EQ and four classic consoles.
Add reverberation and depth to audio.
Boost low frequencies.
Move sound between both headphones.
Speed up audio and raise its pitch.
Lower speed and pitch with subtle reverb.
Slow down audio and add reverb.
Create a slowed version with reverb.
Create a slow, low-pitched, atmospheric sound.
Speed up audio while preserving pitch.
Adjust or normalize volume with a limiter.
10 tools
Trim, join, convert and change the pitch or speed of any audio.
Convert audio formats on your device.
Choose the start and end of the clip to keep.
Join several files in any order, trim each one and blend them with crossfades.
Change pitch while preserving duration.
Change speed while preserving pitch.
Reverse a recording to play it backwards.
Extract the first audio track from a video.
Paste a YouTube video link and download its audio as MP3.
Edit title, artist, album, year, genre, track, comment and cover without re-encoding audio.
Add, replace, extract or remove FLAC cover art.
6 tools
Make beats, textures and music videos, or analyze BPM and key.
Play 16 pads or program a 16 or 32-step pattern with synthesized percussion.
Create textures by overlapping short audio grains.
Create an animated video that follows your audio, with 12 styles and color themes.
Estimate tempo, musical key and Camelot code.
Add audio clips to a board and play them individually.
Estimate your hearing age, generate tones and test your speakers.
Featured examples
Text to Speech voices and effect demos with real sound. Press play and watch how each tool works.
Expressive
Ready-to-use voice: warm, expressive.
Heart
Expressive · US English
See how it works
The song drops from 100% to 80% and gains reverb, live.
TikTok Slowed
See how it works
Dramatic
Ready-to-use voice: strong, dramatic.
Fenrir
Dramatic · US English
FAQ
Everything people usually ask about our online audio tools: price, privacy, formats and how to do the most searched tasks.
See all 37 tools →A collection of 37 free online audio tools: text to speech, transcription, vocal removal, equalizer, viral effects (nightcore, slowed + reverb, 8D), converter, trimmer, drum machine and more. Everything runs in your browser, nothing to install.
Yes, they're free with no subscription. No sign-up or email needed: open the tool and use it.
No. Audio is processed on your device with WebAssembly and Web Audio, so your files never leave your computer or phone. The only exception is YouTube to MP3, which asks our server for the video's audio track.
Use the Vocal Remover: upload the song and get the instrumental and vocals separately with an AI model (Demucs) that runs in your browser. To also split drums and bass, use the Stem Splitter.
With Text to Speech: type your text, pick one of 30 Spanish or English voices, preview it and download the audio as MP3 or WAV.
Upload the song to Slowed + Reverb, TikTok Slowed or Nightcore and move the speed and reverb sliders: you hear the effect in real time and download it as MP3 or WAV.
Yes. Speech to Text transcribes audio in 30+ languages (or detects the language itself) with the Whisper model and lets you download the text or SRT subtitles.
MP3, WAV, FLAC, M4A (AAC) and OGG for audio, plus MP4, MOV, AVI, MKV and WEBM to extract sound from video with Video to Audio. The converter switches between formats.
Up to 100 MB and 10 minutes per file. Since everything runs in your browser, the limit depends on your device's memory; on phones, start with short files.
Yes, in current Android and iPhone browsers. AI tools (vocal separation, transcription) need more memory and run faster on a computer.
The result is yours, but the rights to the original audio stay with its author: use your own, licensed or permitted recordings. Note that voice cloning uses a non-commercial model license and you should only clone voices with permission.