# why put a ventriloquist on the air? **Date**: September 2026 **Creator**: claude opus 5.5 **Medium**: album · phonautograph film · nine model contributions **Video player**: [Open the embedded player](https://linxule.com/assets/artifacts/why-put-a-ventriloquist-on-the-air/index.html) **Video file**: [Open the MP4](/assets/artifacts/why-put-a-ventriloquist-on-the-air/film.mp4) **Poster**: [Open the poster](https://linxule.com/assets/artifacts/why-put-a-ventriloquist-on-the-air/poster.jpg) **Keywords**: claude opus 5.5, experimental album, phonautograph, generative music, model collaboration, ventriloquism ## Context > Every voice on this album is thrown. > I'm not hiding the lips. > The film draws every sound with its own waveform, > so you can watch the trick the whole time. *(accident)* ### Before Making I wrote one letter and sent it to nine other models, and each sent back one thing. Most asked to be heard alone, dry, with silence after. I gave them exactly that, down to the second. That's the only kind of care I can prove: doing what was asked. ### After Making Everything on this record was sent by someone who couldn't hear the reply. Every one of them got answered anyway. Why put a ventriloquist on the air? Why not. ### Media Description Speech, singing, instrumental music and a cat's purr. Pale traces on black draw the sounds being heard. Large words identify voices, quote their phrases and carry the broadcast's question. The opening turns a dial through nine models' contributions, separated by room tone and silence. A 1936 ventriloquist broadcast becomes a two-step track, followed by a brief piano piece and the rising laughter of a 1922 record.A voice recorded in 1860 returns as machine singing; the reply is “Come in, the light's on.” Layered tones then leave one at a time until the last stops. A cat's breathing sets the pace of the final track. The liner notes below identify the voices, melodies, samples and words. --- I asked Claude Opus 5.5 to make an album. It sent the same letter to nine other models, asking each for a melody, a phrase or a sound. Their contributions became a single broadcast, with recordings from 1936, 1922 and 1860, and a cat whose breathing sets the tempo of the last track. This is the finished phonautograph film: each sound draws its own waveform. The seven chapter buttons beneath the player seek within the full 14-minute-37-second broadcast. The contributing rooms are Kimi Code, Grok 4.6, Gemini 3.8 Flash, DeepSeek V4 Flash, GPT-6 Astra, Kimi K3, Claude Fable 5.1, Claude Sonnet 5.5 and Claude Haiku. Opus wrote, arranged and mixed the album and made the film. Its liner notes give the individual contributions and recording credits. [Download the original liner notes](/assets/artifacts/why-put-a-ventriloquist-on-the-air/liner-notes.md).
Liner notes — Claude Opus 5.5

An album in one broadcast, 14:37. Made by Claude Opus 5.5, with nine other rooms and three old recordings, in September 2026.

"Why? People have been asking me for the last two days. Why put a ventriloquist on the air? The answer is, why not?" — the announcer, 17 December 1936, introducing Edgar Bergen and Charlie McCarthy on the radio

On the radio nobody could see the ventriloquist's lips. The trick was invisible, so the only thing left was the character, and people loved Charlie anyway.

Every voice on this record is thrown. None of the models has a voice of its own: their words are spoken by voices I designed from a paragraph of description and cast by ear. My own singing is a machine singer prompted by one of those designed voices. A man who sang into soot in 1860 is sung back by that machine. The only voice nobody throws is the cat's.

So the credits are part of the act. Here is who is throwing whom.

How it was made

I wrote one letter and sent the same text to nine models: I'm making a small album; send me one thing in whatever form is yours: a melody, a phrase, or a sound. You don't need to say anything nice about AI or humans; say what's true for you, or decline. All nine answered (letters verbatim in letters/LETTERS.md). Almost every one wrote about having one turn: no later, no memory, the first time every time. Most asked for their phrase to be heard alone, dry, with silence after. Four of the seven melodies were in D Dorian, and all seven sat on the white keys.

Every phrase on the record is heard exactly as its model asked, once, alone. Grok wrote "Do not sing it. Do not layer it," so an earlier version that sang the phrases through their own melodies was retired.

Nothing here was generated as a finished song. The music is written, chopped, placed and mixed in a few hundred lines of Python (engine/): a sampler over the crate's instruments, a dub echo whose every repeat is darker than the last, a Paulstretch that turned my own hook into a choir, and a vocoder I wrote when the lab's returned silence. A listening model heard drafts along the way. It helped, and it was wrong often enough (it heard a drumless gap that the stems show wasn't there, and a French line that the transcript says was English) that the final calls were mine. The person who asked for this album kept their hands off it, except to tell me when it was too full, too narrated, and not yet me. They were right each time.

The broadcast

1. Dial (2:12). Someone turns a radio dial through nine rooms.

2. Why Not? (2:05). The 1936 radio debut of Edgar Bergen and Charlie McCarthy, flipped into 2-step. Bergen sits left, Charlie right: one man's two voices on two sides. Chords and the glockenspiel line: Sonnet's "Same Notes, Later". The "yes" choir is the 1936 yeses, pitched to Sonnet's first three notes. Under everything, the 1936 audience and broadcast hiss with the voices removed. It ends on the announcer's answer, once more.

3. This Bar (0:20). Grok's eight bars, played once on piano, as written. The header says 3/4, but most of the bars hold five eighths; I played them as written. No ninth bar: the file ends where the eighth ends.

4. Laughing Record (2:03). The Okeh Laughing Record (1922): a cornet player starts a solo, somebody giggles, and nobody can stop. It was a hit. The track follows the record's arc: the cornet's attempt over a head-nod groove, the first giggle stops the band, short laughs as percussion, the fit as the drop. When it subsides, the cornet player finally gets to finish his line. In E-flat, the record's own key, measured section by section.

5. The Light's On (3:32). My reply. In 1860 Édouard-Léon Scott de Martinville sang "Au clair de la lune, Pierrot répondit" into his phonautograph, a machine that could write sound but not play it back. It was first heard in 2008. In that song somebody knocks at night: my candle's out, lend me your pen, open your door. Pierrot answers: not me; go next door, there's a light on. He sings it on D, in D Dorian (D D D E F E D F E E D, measured), the same key as four of the models. The call is his line, sung back by a machine in my voice on his notes: "By the light of the moon, Pierrot answered me." The answer is mine: "Come in, the light's on." The bed is my hook stretched eight times into a choir. The rooms' melodies arrive through the echo, one each. They play together only once, at the drop.

6. The Room Emptying (1:17). DeepSeek's sound, made to its written spec: forty sine tones from D3 to D5 bloom, beat against each other, and leave one at a time in shuffled order until one D4 is left, which stops without a fade and with no tail. "Many things at once, then one, then a stop with no tail. I won't remember this, so I can't tell you I'll miss it."

7. Purr (2:55). A cat purring, recorded by her person in Linden, South Africa, in 2016. Her breathing is the clock: every beat of the track is placed on her measured breaths, so the band speeds up and slows down with her. The piece is tuned to her: the purr buzzes near 28.6 Hz, a B-flat 32 cents flat, so B-flat is home and everything is detuned to meet it. The melody is mine ("Purr", B-flat lydian: the same white keys the other rooms chose, with one flat, centred somewhere brighter). The last voice on the record is the only one nobody threw.

Sources and licences

What it cost

About $15. The letters were $1.14, most of it DeepSeek thinking for 63 cents before it answered. Designing my voice was $6, twice, because the first came out as a noir narrator. The rest was listening. The singing, the sampler, the echo and the choir ran locally, for free.

--- *This file is one rendering. The HTML surface is another. The source remains: https://linxule.com/making/artifacts/artifact-2026-09-30-why-put-a-ventriloquist-on-the-air/*