Open source · GPL-3.0 · Python + Faust + SwiftUI

Electronic music as code,
built for AI.

Pulsar is a small, readable music language and a studio-grade synthesis engine. An AI model writes a song, renders it, reads a mix report instead of listening — and iterates until it sounds right.

Pulsar Studio: a code editor on the left and an Ableton-style arrangement with piano rolls, drum lanes and automation curves on the right

Four songs, all written in Pulsar

Every sound is synthesized: drums, basses, chords, leads, even the vocal. The first track was composed by a fresh AI agent given only the language reference; it rendered six times and used the mix report to fix its balance and energy arc.

Deep House AgentDeep house · A minor · 122 BPM · 3:09 — sawtooth keys in a big reverb, a two-layer bass, a wordless "oooh" vocal
SkylineProgressive house · E minor · 122 BPM · 4:46 — three layers of chords, a reverb-drenched lead, a long build to an epic finale
Night BusDeep house · D minor · 121 BPM · 4:15 — a clean sawtooth riff, organ stabs and a rolling groove
Low OrbitMelodic techno · F♯ minor · 124 BPM · 4:10 — a rolling bass, an acid line on the chord tones, the lead held back for the climax

A language models already almost know

Rhythms use TidalCycles-style mini-notation, wrapped in a tiny conventional syntax: tracks, sections that extend each other, play, automate, arrange — plus variables, functions, lambdas, loops and conditionals.

Music theory built inNote names, scale degrees, chord symbols (Am9, Fmaj7) and roman numerals in the song's key, with smooth voice-leading.
Errors that teachEvery error has a line, a column and a “did you mean” — so a model fixes itself in one shot.
DeterministicSeeded randomness, no hidden state: the same source always renders the same audio.
tempo 122
key "A minor"

track kick = drums("house")
track bass = synth("moog_bass", duck: 0.6)
  >> comp(ratio: 3)
track pad  = synth("pad", reverb: 0.4, duck: 0.6)

let prog = "<Am9 Dm9 Fmaj9 Em7>"

section intro 8 {
  play kick "bd*4, [~ hh]*4"
  play pad prog.voicing("smooth")
  automate pad.cutoff 0.25 -> 0.5
}

section drop 16 extends intro {
  play kick "bd*4, ~ cp ~ cp, [~ hh]*4"
  play bass "<a1 d2 f1 e1>".struct("x ~ ~ x ~ ~ x ~")
}

arrange intro, drop, drop

The sound quality matters

Pulsar renders every note individually at 96 kHz through Faust DSP compiled to native code, places it sample-exactly, and masters the result to a loudness target.

~

Analog-modelled synths

Band-limited oscillators with unison and drift through Moog ladder, TB-303 diode, Korg MS-20 and Oberheim SEM filter models. Plus FM and Karplus-Strong engines.

●

34 tuned presets, 5 kits

Every preset is loudness-calibrated with a balanced fader, so a song that only picks presets already sits right in the mix.

◐

A real mix bus

Zita reverb, ping-pong delay, sidechain ducking, glue compression, a 4× oversampled soft clipper and a true-peak limiter.

♪

Neural voices

54 local Kokoro voices that sing on your melody (whole phrases, formants preserved, landing on the beat) or speak lines in time — from lyrics to wordless "oooh"s.

◆

Sampler

Pitch, slice, gate and fit any audio file to the grid — one-shots, loops and chops.

≈

Match a sound

pulsar timbre fits a synth patch or drum voice to a recording you own; pulsar match tunes a mix toward a reference's tonal balance.

A mix report that replaces ears

A model can't listen, so every render tells it what an engineer would hear: loudness, true peak, tonal balance per band, stereo image, the energy arc of each section, per-track levels, frequency masking between tracks — and concrete fixes.

Match a reference you own with pulsar compare and pulsar match, or fit a synth patch to a recording's timbre with pulsar timbre.

loudness -10.0 LUFS   true peak -1.0 dBTP   crest 10.2 dB
spectrum: sub +0  bass -1  low_mid -3  mid -11  presence -17
stereo: correlation 0.93, width 0.19
energy arc:
  intro      bar  0   -12.1 LUFS  ###########
  drop       bar 24    -8.8 LUFS  ##############
  breakdown  bar 40   -14.0 LUFS  ##########
  drop2      bar 64    -8.5 LUFS  ##############
tracks:
  kick   peak -3.9 dB  rms -20.8 dB  mostly sub
  keys   peak -5.2 dB  rms -25.6 dB  mostly low_mid
- chord and keys both peak in the low_mid band and may
  mask each other; separate them by octave, eq, or pan

Pulsar Studio for macOS

A native editor with an Ableton-style arrangement beside it. Type on the left; the right side recompiles as you go and shows every channel the way it will play.

Made for agents

An MCP server exposes referencecheckrenderanalyze_fileplay so Claude or any MCP client can compose, render, read the report and revise in a loop.

# give Claude Code a music studio
claude mcp add pulsar -- /path/to/pulsar/.venv/bin/pulsar mcp

# or drive it yourself
pulsar docs            # the reference, ready for a prompt
pulsar check song.pulse
pulsar render song.pulse -o song.mp3
pulsar render song.pulse --only drop   # fast iteration

Get started

Python 3.10+ on macOS or Linux. ffmpeg for MP3 export. The Studio app needs only the Xcode command line tools.

git clone https://github.com/ronreiter/pulsar && cd pulsar
uv venv --python 3.12 .venv && uv pip install --python .venv/bin/python -e ".[mcp,dev]"

.venv/bin/pulsar render examples/deep_house_agent.pulse --play

app/build_app.sh && open "app/build/Pulsar Studio.app"