The studio work, done by asking for it.
Most tools give you a rack of plugins and wish you luck. Dhun gives you a producer. You bring a track, a stem or a voice memo, say what is wrong with it, and it does the work, then tells you what it did and why.
Free to start. No card required. We take no rights in your music.
It is a conversation, not a menu.
You do not need to know that the fix is a 3 dB dip at 2.8 kHz with a medium Q. You need the vocal to be audible.
You
here’s the rough mix — the vocal is buried and the room is really obvious
Dhun
Analysed it. The vocal is masked between 2–4 kHz by the guitars, and there is 50 Hz hum plus broadband room noise. De-noising first, then I will carve the guitars and lift the vocal rather than just turning it up.
You
can you make it sit like the reference i uploaded
Dhun
Matched to it — tonal balance and loudness. Yours was 3.2 LU quieter and had more energy below 100 Hz. Have a listen; I can back off the low end if it feels thin now.
You
the third line is flat
Dhun
Line three, "and I never came back" — D3 sung about 40 cents flat across two words. Corrected just those, formants preserved. The rest of the take is untouched.
Illustrative exchanges, in the product’s own voice. The analysis they describe, masking pairs, band energy, cents-flat detection, is what the engine actually reports.
Forty-two tools, and it picks them.
Every one runs on our servers, not in your browser, which is why the phone app can do the same work as the desktop. You say what you want; the producer chooses the tools.
Hear it
- Listen
- Style, tempo feel, mood, the voice, the instruments, and anything that sounds off: in plain words, before it changes a thing.
- Map it
- Tempo, key and sections, and where you sing and where you breathe, so what it adds lands in the gaps.
Build around your voice
- A band that follows you
- The rhythm section, strings or 808s your song needs, on your timing. It asks before your recording goes to the music generator.
- Harmonies in your own voice
- Thirds, fifths or a stack under the chorus, sung by your vocal.
- More of the song
- A sung vocal on your beat, a longer version, or the same song in a new style.
- Something from nothing
- A whole song from a description, or one part, a bassline or a pad, in the key and tempo already there.
Fix the take
- Separate the stems
- Vocals, drums, bass and the rest, pulled apart from a finished mix with Demucs, on our servers.
- Tune it so it still sounds human
- Pitch tracked with SwiftF0 and corrected with Rubber Band, which keeps the formants. It can list what you sang, note by note, and fix only the ones you name.
- Remove the room
- DeepFilterNet takes out hiss, hum, air conditioning and street noise without a gate’s underwater artefacts.
Mix and finish
- Balance the mix, with reasons
- Band energy, sibilance, phase, and which tracks mask each other, and then what it changed and why.
- Master it, or match a record
- A Pedalboard chain for a straight master, Matchering to sit like a reference you name, and an exact loudness target for streaming.
- Arrange and export
- Tracks, clips, fades, automation and tempo; lyrics transcribed from a take; a full-quality render of the whole timeline.
92 plugins. You never have to open one.
The producer knows what each one is for and reaches for the right one: an opto compressor on a vocal, a bus compressor on a drum group. They are all in the editor if you want to drive them yourself, on every plan including free.
- Dynamics15
opto, FET and bus compressors, multiband, transient, gate, clipper
- Time14
plate, hall, spring and shimmer reverbs, tape and ping-pong delays
- EQ12
vintage, dynamic, mid-side, Baxandall, 31-band graphic, notch
- Saturation12
tube, transformer, diode, fuzz, wavefolder, bitcrusher
- Utility11
pan, phase, polarity, mono-maker, M/S matrix, metering
- Modulation11
chorus, flanger, phaser, rotary, tremolo, ring mod
- Mastering7
master EQ, bus comp, stereo enhance, limiter, dither, reference match
- Creative7
granular, glitch, lo-fi, sidechain
- Pitch3
correction, doubler, octaver
A real DAW, for when you want one.
Multi-track timeline, insert chains, automation, offline render. It is a genuine editor, not a toy.
It is also optional, on purpose. The editor came first and got too complicated for the people it was for. Everything it can do, the producer can do by being asked, so the editor is there when you want to move a fader yourself and out of the way when you do not.
Web only: live playback uses Web Audio, a browser technology. The phone apps do the same work on our servers instead.
Multi-track timeline
Arrange, trim, fade, automate.
Insert chains
Any of the 92, in any order, on any track.
Full-quality render
An offline bounce of exactly what you hear.
We take no rights in your music.
Nothing you upload or make here becomes ours. We do not take a cut, we do not claim a share of publishing, and we do not need a licence to your masters to run a compressor on them.
We are also straight with you about the part that is genuinely unsettled. For audio you upload and we process, the result is yours. For audio generated from a prompt, copyright is not ours to promise: the US Copyright Office does not register work lacking human authorship, and the generation providers grant a commercial licence rather than ownership. Anyone telling you otherwise is making a promise they cannot keep.
Bring a track and ask it something.
Free to start, and counted rather than timed: 1 song generation, 3 stem splits, 1 master, 20 producer replies and 15 audio processing runs. No clock, no card.