Cochlea MCP server

cochlea

A headless audio engine for agents. Write a score as data, render it offline to deterministic PCM, then listen through numbers — loudness, onsets, pitch, key, spectrograms — and assert what you heard. Compose → render → probe → verify, with no human ear (and no audio device) in the loop.

What the agent sees: the mel spectrogram of examples/scores/firstlight.ron — the score used in the example below — after render and probe. No PCM in sight.*

use cochlea_score::*;

let score = Score::new(SampleRate(48_000), Ppq(960))
    .time_signature(4, 4)
    .tempo(Ticks(0), Bpm(120.0))
    .track("lead", Instrument::preset("saw_lead"))
    .note("lead", bar(1).beat(1), Dur::quarter(), Pitch::A4, Vel(96))
    .automate("lead", Param::CUTOFF_HZ,
        keys![(bar(1), 400.0, ease_in_out()), (bar(3), 4_000.0)]);

let rendered = cochlea_render::render(&score)?;
rendered.write_wav("mix.wav")?;

use cochlea_verify::{VerifyExt, Tol, Ms, Cents, Db};
let report = rendered.verify(&score)
    .true_peak_below(-1.0)
    .pitch_matches_score("lead", Cents(10.0))
    .monotone("lead", Param::CUTOFF_HZ, bar(1)..bar(3))
    .silent_after(bar(5))
    .run();
assert!(report.passed);

Or entirely from the command line, score as RON:

cochlea render score.ron --out mix.wav --stems stems/ --verify
cochlea probe input.wav --json report.json --spectro spec.png
cochlea probe input.wav --digest --window-ms 500
cochlea probe input.mp3 --from 42.0 --to 44.5      # zoom into a window, any format
cochlea diff a.wav b.wav --tier2 --spectro delta.png
cochlea lint score.ron
cochlea spectro input.wav --out spec.png --annotate  # draw beats/onsets/pitch on the image
cochlea import song.mid --out score.ron              # SMF -> score, timing exact
cochlea transcribe solo.wav --out score.ron          # audio -> score, the inverse of render
cochlea reference    # the full score-authoring reference, generated from the live preset bank

cochlea probe works on any WAV, plus FLAC (decoded bit-exact), mp3, and ogg — still without ffmpeg, and with no score required. That's the front door: point it at audio you didn't render, and you get the same JSON report and spectrogram an agent uses to review its own work.

How an agent listens

compose → render → probe (JSON) → spectrogram (one vision call) → verify

key, silence, clipping) — cochlea probe mix.wav --json report.json. No image, no audio: the agent reads numbers.

1. compose a score as data (RON, or the Rust builder above).
2. render it to deterministic PCM — cochlea render score.ron --out mix.wav.
3. probe the mix into a compact JSON report (loudness, onsets, pitch,

spec.png renders one small PNG the agent reviews in a single vision call instead of reasoning about raw samples.

1. look, when numbers aren't enough — cochlea spectro mix.wav --out

embedded assertions and exits nonzero on failure. An agent can retry on its own, without a human confirming "yes, that sounds right."

1. verify — cochlea render score.ron --verify runs the score's

Shortened. The full README is on GitHub.