{
  "schema_version": 1,
  "release_date": "2026-10-12",
  "publication_scope": "ten-curated-full-conversation-pairs",
  "output_publication_clearance": "author-confirmed-2026-10-12",
  "selection": "Curated technical eligibility and duration diversity, not a random evaluation sample or a listening-quality score. See the audio-examples guide.",
  "condition": "SeedVC voice conversion followed by F5-TTS complete-turn lexical editing and full conversation reconstruction.",
  "transcoding": "MP3 128 kb/s. Full waveform, no trim, silence removal, gain adjustment, denoising, or speed change.",
  "datasets": {
    "primock57": {
      "name": "PriMock57",
      "setting": "Mock primary-care consultation",
      "url": "https://github.com/babylonhealth/primock57",
      "revision": "cd2ac707ad03cb4d2531f4ec6b90c659bf4357c5",
      "license": "CC-BY-4.0",
      "source_note": "Original input is a constructed mixture of the doctor and patient role tracks."
    },
    "fareez": {
      "name": "Fareez",
      "setting": "Simulated respiratory interview",
      "url": "https://doi.org/10.6084/m9.figshare.16550013.v1",
      "revision": "10.6084/m9.figshare.16550013.v1",
      "license": "CC0-1.0",
      "source_note": "Original input is the respiratory interview recording used in the evaluation."
    },
    "simsamu": {
      "name": "SIMSAMU",
      "setting": "Simulated emergency-dispatch call",
      "url": "https://huggingface.co/datasets/medkit/simsamu",
      "revision": "6b639431f658d636c30dbf342074d723bf303e0f",
      "license": "MIT",
      "source_note": "Original input is the French dispatch-call recording used in the evaluation."
    }
  },
  "examples": [
    {
      "id": "example-01",
      "dataset": "primock57",
      "source_id": "day4_consultation04_mixed",
      "evaluation_id": "primock57_mixed_0038",
      "language": "en",
      "speaker_count": 2,
      "edited_turns": 2,
      "planned_edit_count": 2,
      "media": {
        "original": {
          "file": "example-01-original.mp3",
          "duration_sec": 393.3,
          "encoded_duration_sec": 393.372,
          "sample_rate": 16000,
          "channels": 1,
          "bytes": 6294572,
          "sha256": "441ffddd8e8a5db30630671cf8bc25817e5ea0b2a2eed59798de0497ed5084f4",
          "waveform_sha256": "5e5b8d0865a9f70f82c1bd7f264f58d92a4378614e16772a584daaaa19c76a57",
          "rms_dbfs": -20.994884
        },
        "final": {
          "file": "example-01-final.mp3",
          "duration_sec": 392.78907,
          "encoded_duration_sec": 392.85551,
          "sample_rate": 22050,
          "channels": 1,
          "bytes": 6286149,
          "sha256": "bf6bffe8dd89a7ad8f5ce51b34dbb6e30dc228e2568e158c83e001cdc137d821",
          "waveform_sha256": "7dd92ee93c9f47540900c5b1d01d43b79322b1dab31de7d8f561eeb1518fb80e",
          "rms_dbfs": -16.401295
        }
      }
    },
    {
      "id": "example-02",
      "dataset": "primock57",
      "source_id": "day1_consultation03_mixed",
      "evaluation_id": "primock57_mixed_0002",
      "language": "en",
      "speaker_count": 2,
      "edited_turns": 1,
      "planned_edit_count": 1,
      "media": {
        "original": {
          "file": "example-02-original.mp3",
          "duration_sec": 544.32,
          "encoded_duration_sec": 544.392,
          "sample_rate": 16000,
          "channels": 1,
          "bytes": 8710892,
          "sha256": "310f4237cb9593c1a1505525e7bb1c857488e447b2755dc20654ff882d59b4ba",
          "waveform_sha256": "f93f348f499d4d770278cadf3d3dcb9d916da2956cae9577dff7d922905514d0",
          "rms_dbfs": -21.937851
        },
        "final": {
          "file": "example-02-final.mp3",
          "duration_sec": 541.23873,
          "encoded_duration_sec": 541.309388,
          "sample_rate": 22050,
          "channels": 1,
          "bytes": 8661411,
          "sha256": "600ebc47ef3f158c9bbd32471601016cbd8bfb4bd4d0af036119e74b71726a36",
          "waveform_sha256": "e0e72faa6bef6fc22847d60613710e9439e6bb207cff549f65404f0c42c94f31",
          "rms_dbfs": -15.471991
        }
      }
    },
    {
      "id": "example-03",
      "dataset": "primock57",
      "source_id": "day3_consultation09_mixed",
      "evaluation_id": "primock57_mixed_0033",
      "language": "en",
      "speaker_count": 2,
      "edited_turns": 4,
      "planned_edit_count": 5,
      "media": {
        "original": {
          "file": "example-03-original.mp3",
          "duration_sec": 712.44,
          "encoded_duration_sec": 712.512,
          "sample_rate": 16000,
          "channels": 1,
          "bytes": 11400812,
          "sha256": "b454bf60443b51f50dc7de68576d99bdb7ef449d641119f4592d9dad245c3471",
          "waveform_sha256": "04c66c2303f6f25dc6650442cbfdba15d1d54e2d44b8c99f315d89ad2d88fda4",
          "rms_dbfs": -22.164487
        },
        "final": {
          "file": "example-03-final.mp3",
          "duration_sec": 708.77678,
          "encoded_duration_sec": 708.832653,
          "sample_rate": 22050,
          "channels": 1,
          "bytes": 11341783,
          "sha256": "9d12ee91624e217eb689d2e811b8a54736fa8d7c2554aa9d19409ae629122878",
          "waveform_sha256": "e35c8f89b3eee98d88035ad0b07e8bada4771e1abdbe669bb8a74e139afcf073",
          "rms_dbfs": -19.07846
        }
      }
    },
    {
      "id": "example-04",
      "dataset": "fareez",
      "source_id": "RES0217",
      "evaluation_id": "fareez_0271",
      "language": "en",
      "speaker_count": 2,
      "edited_turns": 6,
      "planned_edit_count": 7,
      "media": {
        "original": {
          "file": "example-04-original.mp3",
          "duration_sec": 513.843125,
          "encoded_duration_sec": 513.936,
          "sample_rate": 16000,
          "channels": 1,
          "bytes": 8223596,
          "sha256": "65da5a9621b898c1c7f26e7290900d63db46177452d4b695969c0dbbb58b1b03",
          "waveform_sha256": "786b142c0d526f547bf6b5a4d92278507f58e536186f6d9ec31aed106c2034dc",
          "rms_dbfs": -22.242325
        },
        "final": {
          "file": "example-04-final.mp3",
          "duration_sec": 509.953197,
          "encoded_duration_sec": 510.014694,
          "sample_rate": 22050,
          "channels": 1,
          "bytes": 8160696,
          "sha256": "19be0c8d4f3353a48bd4ae2b3678b1b5d95db8057ca3dd1093ec8effa891639d",
          "waveform_sha256": "b68a6d798a1ef60db95fbd4d6ecc3377f6a95411821ef9e3936e0ecc8cc70e8c",
          "rms_dbfs": -16.951411
        }
      }
    },
    {
      "id": "example-05",
      "dataset": "fareez",
      "source_id": "RES0068",
      "evaluation_id": "fareez_0124",
      "language": "en",
      "speaker_count": 2,
      "edited_turns": 1,
      "planned_edit_count": 1,
      "media": {
        "original": {
          "file": "example-05-original.mp3",
          "duration_sec": 664.972813,
          "encoded_duration_sec": 665.064,
          "sample_rate": 16000,
          "channels": 1,
          "bytes": 10641644,
          "sha256": "465491b540d14c83ced4d9d4024c539e81e33b4be76afbecc505497db401fff5",
          "waveform_sha256": "367e2c7d9c7d1b3a831d22901d19a5f1a9ff9f58a44a8649ba50817235b38fb7",
          "rms_dbfs": -22.960132
        },
        "final": {
          "file": "example-05-final.mp3",
          "duration_sec": 653.332698,
          "encoded_duration_sec": 653.400816,
          "sample_rate": 22050,
          "channels": 1,
          "bytes": 10454874,
          "sha256": "e35774d34d4ccbd3a1f26a709736c35b320c3c6107aa9e6f0b809d1f8ff431ce",
          "waveform_sha256": "1b5f41658b8e1713e3fd0804b71fa6d247a8291a6b7b7c81850e9b0b42dcc776",
          "rms_dbfs": -17.429901
        }
      }
    },
    {
      "id": "example-06",
      "dataset": "fareez",
      "source_id": "RES0123",
      "evaluation_id": "fareez_0178",
      "language": "en",
      "speaker_count": 2,
      "edited_turns": 2,
      "planned_edit_count": 2,
      "media": {
        "original": {
          "file": "example-06-original.mp3",
          "duration_sec": 742.380875,
          "encoded_duration_sec": 742.464,
          "sample_rate": 16000,
          "channels": 1,
          "bytes": 11880044,
          "sha256": "dfef8ac3d8ed05937d3c0f9ef1dc680d2183d2b68abf00ae3f07cd4baeb0d057",
          "waveform_sha256": "3debb348386ab4bcf7a73b49c2e75554e08e30b57c959dc431ea59cfe0f8200e",
          "rms_dbfs": -22.989448
        },
        "final": {
          "file": "example-06-final.mp3",
          "duration_sec": 739.430023,
          "encoded_duration_sec": 739.500408,
          "sample_rate": 22050,
          "channels": 1,
          "bytes": 11832467,
          "sha256": "8c68adab918ea534e6496009f1924ca9de623c43d5f52ea370e933904a438406",
          "waveform_sha256": "d32ffcef413904d5b2c56e9211257db80082a859992974d27a1c049a9ad524b5",
          "rms_dbfs": -19.780216
        }
      }
    },
    {
      "id": "example-07",
      "dataset": "fareez",
      "source_id": "RES0011",
      "evaluation_id": "fareez_0069",
      "language": "en",
      "speaker_count": 3,
      "edited_turns": 2,
      "planned_edit_count": 2,
      "media": {
        "original": {
          "file": "example-07-original.mp3",
          "duration_sec": 905.699375,
          "encoded_duration_sec": 905.796,
          "sample_rate": 16000,
          "channels": 1,
          "bytes": 14493356,
          "sha256": "2f0ad32e0960db9e940402566254de6dfdf575027531cb4a59ff5b91463c0ca2",
          "waveform_sha256": "8af3d77ba271ad13fade0c0dc6e60aa8a7a2eaf98d9b46ee6876ea8f50ea87ee",
          "rms_dbfs": -23.706497
        },
        "final": {
          "file": "example-07-final.mp3",
          "duration_sec": 888.366122,
          "encoded_duration_sec": 888.42449,
          "sample_rate": 22050,
          "channels": 1,
          "bytes": 14215252,
          "sha256": "66968283ebfd9f373f97500c93ef27fc715a03fb1e4603d7fe1285617e868770",
          "waveform_sha256": "269e8f4d589f4afb58945b7e1b1b5cdca63e93d00c7f1dbd5871dd5d24362f90",
          "rms_dbfs": -20.634119
        }
      }
    },
    {
      "id": "example-08",
      "dataset": "simsamu",
      "source_id": "dj_2022_avp_scooter",
      "evaluation_id": "simsamu_0004",
      "language": "fr",
      "speaker_count": 2,
      "edited_turns": 1,
      "planned_edit_count": 1,
      "media": {
        "original": {
          "file": "example-08-original.mp3",
          "duration_sec": 122.624,
          "encoded_duration_sec": 122.724,
          "sample_rate": 16000,
          "channels": 1,
          "bytes": 1964204,
          "sha256": "95329bd4a27e634ce03f103b3c90435dedc0b04378a1305ce1015d4e4ef07b5e",
          "waveform_sha256": "fd7ee771a8f4019a06890b699c63854d23f4262fe7e6c1800cc4fe23a05dbc52",
          "rms_dbfs": -44.9905
        },
        "final": {
          "file": "example-08-final.mp3",
          "duration_sec": 121.316009,
          "encoded_duration_sec": 121.39102,
          "sample_rate": 22050,
          "channels": 1,
          "bytes": 1942717,
          "sha256": "d3afc76f55e3bc529df7c7f49d4703960f9eafb36603c247f40f9c174590dc9a",
          "waveform_sha256": "6ea787436a4e4c7cae84e94951ff2a47000fb71f8d99127d01aa55e3885d9ac1",
          "rms_dbfs": -19.906888
        }
      }
    },
    {
      "id": "example-09",
      "dataset": "simsamu",
      "source_id": "dj_2022_douleur_thorax",
      "evaluation_id": "simsamu_0010",
      "language": "fr",
      "speaker_count": 4,
      "edited_turns": 1,
      "planned_edit_count": 2,
      "media": {
        "original": {
          "file": "example-09-original.mp3",
          "duration_sec": 171.648,
          "encoded_duration_sec": 171.72,
          "sample_rate": 16000,
          "channels": 1,
          "bytes": 2748140,
          "sha256": "be565ac92d0eae2883994e75f403e9bba5b1c4b7774adf437f48aff6bc4cd387",
          "waveform_sha256": "cb4b7f908c9d44c4a0bd98b23b48a3bc7a55fa52c0f7e49d92d07a95a0d1bd28",
          "rms_dbfs": -41.408445
        },
        "final": {
          "file": "example-09-final.mp3",
          "duration_sec": 169.220363,
          "encoded_duration_sec": 169.273469,
          "sample_rate": 22050,
          "channels": 1,
          "bytes": 2708836,
          "sha256": "fd148edc663f868e5eb3b4fff16912ac33b7e37858f1e0e35be32de0a059be85",
          "waveform_sha256": "243cfc7f2356a27b9f4bcc05e5e23c5fc9894748ad59a730a5739cab2d614479",
          "rms_dbfs": -16.676998
        }
      }
    },
    {
      "id": "example-10",
      "dataset": "simsamu",
      "source_id": "dj_2022_tetanie_2",
      "evaluation_id": "simsamu_0020",
      "language": "fr",
      "speaker_count": 3,
      "edited_turns": 1,
      "planned_edit_count": 1,
      "media": {
        "original": {
          "file": "example-10-original.mp3",
          "duration_sec": 257.536,
          "encoded_duration_sec": 257.616,
          "sample_rate": 16000,
          "channels": 1,
          "bytes": 4122476,
          "sha256": "ce6a50bbdadc696c579c3a0bf75d5e711c26b6e4e5e147861f3b632ea944232f",
          "waveform_sha256": "96577d72bbd87fac92a94271683f78471ed8da690df06169b9bd827410a662c0",
          "rms_dbfs": -45.627674
        },
        "final": {
          "file": "example-10-final.mp3",
          "duration_sec": 257.04839,
          "encoded_duration_sec": 257.123265,
          "sample_rate": 22050,
          "channels": 1,
          "bytes": 4114433,
          "sha256": "49b41a5f8d583d7ffb7e9e99f8b25b7e490bfc555b64ae3ddd7d42b28de97932",
          "waveform_sha256": "348cfa4ba8762c79b8df44cef46bf6023b0078c18cbd6707140360598d2047dc",
          "rms_dbfs": -20.62622
        }
      }
    }
  ]
}