Whale & Dolphin
Orchestra

Whale & Dolphin Orchestra.

Working prototype

Marine biodiversity has a sound of its own. This orchestra transforms real recordings into music for human ears, guided by measured rhythms and pitch contours. The prototype plays a small selection of short excerpts from open research collections. Choose your musicians on the map, or hear a finished piece.

Select recordings on the map and listen here.
01 / The ocean stage

Every voice has a place.

Preparing the programme…
Select a site to add a voice. Scroll or pinch to explore.
02 / Your ensemble

The orchestra

Arrangement

    Choose recordings to check saved versions.

    Choose Base for a full composition or Stable Audio for a faster alternative. Each model keeps its own version.

    Behind the listening experience

    From a voice
    to a musical score.

    Real recordings enter the system. Signal analysis measures their phrases. Those measurements become a playable guide, which a generative model uses to compose music.

    01 / Input · Recorded

    Listen to the animal.

    Short excerpts of hydrophone recordings: humpback song, dolphin whistles, sperm-whale codas, and killer-whale calls.

    Audio + recording location
    02 / Schema · Measured

    Measure the phrase.

    Onsets, durations, click groups, and pitch contours are extracted from audio. Tonal calls and clicks have different representations.

    Events + time + frequency
    03 / Guide · Constructed

    Give it an instrument.

    Contours become tones and clicks become mallet strikes. Each player's instrument and register are combined with your trims, timing, and arrangement.

    A playable combined guide
    04 / Output · Generated

    Compose a response.

    Your selected model transforms the combined guide into music. A deterministic response provides a comparison that follows the measured events by construction.

    Separate, playable audio stems

    The diagrams above illustrate the process. The spectrograms and phrase marks below come from the selected recording.

    Research foundation / DCLDE

    A diversity of calls,
    populations, and places.

    We selected excerpts from the DCLDE killer-whale detection and classification collection for its regional and acoustic diversity. Its authors describe it as the largest curated DCLDE audio-and-annotation dataset at the time of publication in 2025.

    Dataset paper
    1.6 TBaudio in the research collection225,000+annotations reported by its authors

    These figures describe the research collection. This prototype uses a small selection of its excerpts, together with excerpts from earlier DCLDE workshops (2011–2022), the Alfred Wegener Institute's polar recordings on PANGAEA, and Orcasound, OpenWhistle and Dominica Sperm Whale Project recordings, to bring different waters and species into the same composition. The source collections are listed below.

    Human and marine-mammal hearing differ. Registers can be shifted into a musical range, while measured event times and contour shapes remain the guide. The timing scores below test how closely the generated music follows the measured event times.

    NOAA: the variety of marine mammal sounds
    Look inside a phrase

    The recording becomes the score.

    What is being tested?

    Does the music follow the phrase?

    Timing scores compare musical onsets with the animal's measured onsets, against the same output shifted in time. They help distinguish a response to this phrase from music that simply sounds appropriate.

    What is the artwork?

    A musical interpretation.

    The recordings are animal sounds. The measurements are signal analysis. The guide is a human-designed mapping and the composition is generated music. This process does not decode animal meaning.

    Development & models

    Tools, choices and authorship.

    We used Claude Code and OpenAI Codex to help develop and debug the software. Livia Zaharia and Anton Kulaga define the project concept, artistic direction and methodological choices, make the final decisions, and take responsibility for the work.

    Measuring the recordings. Signal analysis extracts call timing and pitch contours. Our code maps those measurements to instruments and registers, then combines them into a playable audio guide.

    Generating the music. We run ACE-Step 1.5's Base and Turbo checkpoints locally. Base uses 50 steps and guidance controls; Turbo provides an eight-step preview whose instrumentation and detail can differ. We also offer Stable Audio 3 Small Music, a smaller eight-step model. Each model receives the same guide, caption, duration and seed, with its own transformation controls, and keeps a separate generated version. The diffusion transformer generates music from the combined audio guide and a caption. Our current pipeline leaves the model's optional language-model planning stage disabled.

    Checking the response. A deterministic musical response provides a comparison, and timing scores test how closely the generated music follows the measured events. Original recordings, constructed guides and generated music remain separately playable.

    Jewellery methods and digital tests are on the Sound to silver page.

    Sound sources

    Where the voices come from.

    The prototype plays a few dozen excerpts, each under half a minute. They are a small subset, chosen by hand from open collections that hold years of recordings and many thousands of annotated calls. Each card says what we took.

    • Orcasound

      Haro Strait humpback song

      Humpback song at the Orcasound Lab hydrophone, with Emily Vierling's call annotations.

      orcasound.net
    • OpenWhistle

      Eilat dolphin whistles

      Bottlenose dolphin whistle sequences recorded at Dolphin Reef, Eilat.

      OpenWhistle on Hugging Face
    • DSWP

      Dominica sperm-whale codas

      Coda clips from the Dominica Sperm Whale Project, placed in sequence with short silences we added.

      DSWP on Hugging Face
    • PhyloPic

      Species silhouettes

      Chair and legend silhouettes by Chris huh (CC BY-SA 3.0) and Margot Michaud (CC0).

      phylopic.org

    Only the animal recordings come from these collections. The guides, the constructed responses and the generated music are made by this project.

    Fine-tune playersTiming, trims, gain & register

      Add players in the concert hall to adjust their phrases here.

      Composition model
      Task

      In the first study, cover follows the guide's timing more closely. Lego tracks mostly ignore it.

      Engine logSession activity
      Nothing composed in this session yet.

      Sound to silver.

      Inline uses your supplied base with an open gap between the ends and a smooth middle spine. Recording amplitude sets the outward height; frequency sets the spacing of the peaks. Smooth transverse connections appear at the wave peaks while the outer rails stay fixed. Compare Neutral and Sound, or press Play sound to listen.

      Preparing the ring…

      Livia Zaharia's Inline Ring, a silver parametric ring photographed at an angle
      Inline Ring · cast silver, 2022. Photograph by Livia Zaharia.

      Sound shapes these forms through artistic mappings chosen by Livia. The same approach can be applied to other forms she designs.

      Planned editions. Website visitors will be able to choose a recording and download its sound-shaped STL. At exhibitions, a small batch of 3D printed pieces made from the default sound combinations will be available to take or buy to support the research.

      A limited cast-silver edition is planned for visitors who donate to marine-science and conservation causes. Each exhibition will name the beneficiary and state the donation amount.

      Jewellery / Digital tests

      Digital jewellery tests.

      Earlier whole-ring bending tests checked finger openings, wall thickness and gaps on Livia's Inline and Roots models. The current additive previews still need their parts joined and checked before fabrication.

      Hardata II: keeping a whistle's contour.

      The pilot asks which features of a dolphin whistle can survive a compact inscription. Its input is the annotated pitch contour from an OpenWhistle recording. We sample the contour at 32 points, store each pitch in 8 bits, and add 16 bits for start and end times: 272 bits per whistle. A constant-amplitude tone reconstructed from those measurements is the output. A separate version maps time around a ring band and pitch across its width, forming a groove.

      Using the dolphin-trained OpenWhistle encoder, we trained a classifier on original recordings and tested it on the same 420 held-out whistles in each condition. Recording sessions are separate across the training, validation and test sets. The labels are six whistle types: five signature types associated with named dolphins and one shared non-signature type. They identify types, rather than verified callers.

      Hardata II pilot · 7 October 2026. Macro-F1 averages the classification score equally across the six whistle types; it is not percentage accuracy.
      Audio testedMacro-F1
      Original recordings0.822
      Tones from 272-bit pitch contours0.617
      Reversed contours0.229
      Flat tones at each whistle's mean pitch0.256
      Amplitude-only reconstruction, following Hardata (2021)0.096

      Some distinctions between whistle types remain in the contour tones. Reversing or flattening the contour reduces the classifier's score, suggesting that contour shape matters to this model. This tests a model's response, not what dolphins hear or what their calls mean.

      The groove version also retained type distinctions after simulated blur and surface noise. That digital simulation does not establish casting tolerance: printing, casting and polishing tests remain to be done.

      About

      Architecture, nature
      and measured sound.

      Whale & Dolphin Orchestra grows from Livia Zaharia's practice as a Romanian architect, established parametric jewellery designer and science-art artist. It brings her work with computational form into marine sound and silver. Anton Kulaga contributes bioinformatics, longevity research and open-source software.

      Portrait of Livia Zaharia
      Architect · parametric jewellery designer · science-art artist

      Livia Zaharia

      A Romanian architect, Livia works across computational design, contemporary jewellery and science art. Under Paral Design, she uses Grasshopper, COMPAS and Python to generate forms, then 3D-prints and casts them mainly in silver, sometimes with amber, walnut husks or quartz. Her jewellery has been shown at Romanian Jewelry Week each year since 2021.

      Portrait of Anton Kulaga
      Longevity researcher · entrepreneur · open-source developer

      Anton Kulaga

      Anton works in longevity research and bioinformatics at the Systems Biology of Aging Group. He builds open-source computational tools. For this project, he built the map, the recording-analysis pipeline, the music generation software and the website.

      Selected work · jewellery and digital art

      From cell-inspired jewellery to digital genetics.

      Livia Zaharia · Romanian Jewelry Week 2025

      It's Just a Cell Life

      The Biology collection follows different stages and parts of a cell through jewellery. The Nanot of Power is one sterling-silver pendant among several works.

      Open lattice of Livia Zaharia's The Nanot of Power pendant
      The Nanot of Powersterling silver
      Mitoring, a mitochondria ring with amber and sterling silver by Livia Zaharia
      MitoringMitochondria ring · amber and sterling silver
      The Nut of Power pendant in walnut, amethyst and brass by Livia Zaharia
      The Nut of Powerwalnut, amethyst and brass
      The Dark Nut of Power pendant in walnut and copper by Livia Zaharia
      The Dark Nut of Powerwalnut and copper
      Shared digital project · Livia Zaharia & Anton Kulaga

      Materialized Enhancements

      An interactive science-art experience made with GlucoseDAO and Longevity Genie. Visitors explore biological traits; Livia shapes their selections into printable crystals, while Anton contributes biology and software.

      Screenshot of enhancement.bio showing the gene library and human enhancement profile
      Website preview
      Shared digital environment · Livia Zaharia & Anton Kulaga

      Livistone

      A walk-through 3D town where Livia's jewellery forms grow into architecture.

      Central buildings in the Livistone walk-through 3D town
      Walk-through 3D environment
      Open source

      The code and the method are public.

      Livia-Zaharia/whales

      The repository holds this website, the Python engine that measures the recordings and composes the pieces, and the research behind both: datasets, models, art precedents and the silver studies.

      Recordings come from the Alfred Wegener Institute's polar recordings on PANGAEA, the NOAA DCLDE workshop datasets, Orcasound, OpenWhistle and the Dominica Sperm Whale Project. Photographs of Livia's jewellery and her portrait: Livia Zaharia. To talk about the project, write to Livia on Instagram or LinkedIn, or open an issue on GitHub.