GENERATION INPUTS, NOT A VERIFIED SCORE
{
  "task_type": "text2music",
  "instruction": "Fill the audio semantic mask based on the given conditions:",
  "reference_audio": null,
  "src_audio": null,
  "audio_codes": "",
  "caption": "Original simple acoustic ballad, a single clear sung English voice closely following every supplied lyric line, minimal fingerpicked guitar and soft bass only, no wordless introduction, no adlibs, no extra repeated lines, clear diction, unhurried short phrases, 90-second complete verse chorus song, gentle ending. No artist imitation.",
  "global_caption": "",
  "lyrics": "I called across the water in the rain,\nThe hills sent back a little of the strain.\nSome words came home, some wandered out of sight,\nI held the ones that reached me through the night.\n\nSay it slowly, let it ring,\nHear the heart of everything.\nNot the sound we hoped to hear,\nBut the small true note still clear.\n\nWe set the cup upon the kitchen shelf,\nAnd let the quiet answer for itself.\nA crooked handle still could hold the tea,\nA little care could show what it could be.\n\nSay it slowly, let it ring,\nHear the heart of everything.\nNot the sound we hoped to hear,\nBut the small true note still clear.\n\nAt dawn we took the softer path uphill,\nThe echo left us something warmer still.\nA song is more than all we meant to say,\nWe listen, and we learn another way.",
  "instrumental": false,
  "vocal_language": "en",
  "bpm": 90,
  "keyscale": "C major",
  "timesignature": "4",
  "duration": 90,
  "enable_normalization": true,
  "normalization_db": -1.0,
  "fade_in_duration": 0.0,
  "fade_out_duration": 0.0,
  "latent_shift": 0.0,
  "latent_rescale": 1.0,
  "inference_steps": 8,
  "seed": 202611070131,
  "guidance_scale": 7.0,
  "use_adg": false,
  "cfg_interval_start": 0.0,
  "cfg_interval_end": 1.0,
  "shift": 1.0,
  "infer_method": "ode",
  "sampler_mode": "euler",
  "velocity_norm_threshold": 0.0,
  "velocity_ema_factor": 0.0,
  "dcw_enabled": null,
  "dcw_mode": "double",
  "dcw_scaler": 0.05,
  "dcw_high_scaler": 0.02,
  "dcw_wavelet": "haar",
  "timesteps": null,
  "repainting_start": 0.0,
  "repainting_end": -1,
  "chunk_mask_mode": "auto",
  "repaint_latent_crossfade_frames": 10,
  "repaint_wav_crossfade_sec": 0.0,
  "repaint_mode": "balanced",
  "repaint_strength": 0.5,
  "retake_seed": null,
  "retake_variance": 0.0,
  "flow_edit_morph": false,
  "flow_edit_source_caption": "",
  "flow_edit_source_lyrics": "",
  "flow_edit_n_min": 0.0,
  "flow_edit_n_max": 1.0,
  "flow_edit_n_avg": 1,
  "audio_cover_strength": 1.0,
  "cover_noise_strength": 0.0,
  "thinking": false,
  "lm_temperature": 0.85,
  "lm_cfg_scale": 2.0,
  "lm_top_k": 0,
  "lm_top_p": 0.9,
  "lm_negative_prompt": "NO USER INPUT",
  "use_cot_metas": false,
  "use_cot_caption": false,
  "use_cot_lyrics": false,
  "use_cot_language": false,
  "use_constrained_decoding": true,
  "cot_bpm": null,
  "cot_keyscale": "",
  "cot_timesignature": "",
  "cot_duration": null,
  "cot_vocal_language": "unknown",
  "cot_caption": "",
  "cot_lyrics": ""
}

INTENDED ARRANGEMENT
Intended sparse acoustic ballad4/4 at90BPM inCmajor. Verse C–Am–F–G and chorus F–C–G–C. Shorter lyric and sparse arrangement aim to improve intelligibility, but exact rendered words/notes remain unverified. No event-level score control.

VERIFIED TECHNICAL OUTPUT
{
  "requested_seconds": 90,
  "lyrics_characters": 762,
  "lyrics_tokens": 188,
  "seconds": 90.0,
  "sample_rate": 48000,
  "channels": 2,
  "peak": 0.8912353515625,
  "rms": 0.1580994407490113,
  "finite": true,
  "generation_seconds": 236.77454018592834,
  "full_listening_verified": false,
  "exact_lyrics_verified": false,
  "exact_notes_verified": false,
  "m4a_probe": {
    "programs": [],
    "stream_groups": [],
    "streams": [
      {
        "codec_name": "aac",
        "sample_rate": "48000",
        "channels": 2
      }
    ],
    "format": {
      "duration": "90.000000"
    }
  },
  "m4a_sha256": "438675bca7106e82c71b2b07229689b60444f1a4dab2df66a1fc9f77dadf48d3"
}

LIMITATIONS
No full listening review, exact lyric verification, or note-for-note transcription. Intended chords and notes are not claimed as rendered. ACE-Step1.5 code/model MIT; Qwen embedding Apache2.0. Training provenance is mixed, not exclusively public domain. No paid generation service.

WAV DELIVERY AND AUTOMATED WORD CHECK
Matching WAV is original generated PCM16 stereo48kHz, verified90.000seconds; M4A is its AAC derivative. Local Whisper base.en processed the full track and recovered some chorus/closing words, but omitted or altered other phrases. A shorter sparse arrangement did not establish exact lyric fidelity. No verified listening or word-for-word PASS is claimed.