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 warm chamber pop song, clear intimate sung English lead, acoustic guitar, soft piano, pizzicato strings, rounded bass and light restrained drums. Spacious call and response, hopeful reflective mood, recurring chorus, natural unhurried diction, full two minute song with gentle resolved ending. No artist imitation.",
"global_caption": "",
"lyrics": "The red ran down to greet a patch of blue,\nAnd made a shade that neither of them knew.\nWe watched the brush go wandering off the line,\nThen found a place for every crooked sign.\n\nA drum came softly knocking at the gate,\nThe strings replied, the voices chose to wait.\nOne empty beat was all they had to share,\nIt made a little breathing room of air.\n\nCome as you are, bring what you know,\nThe quiet roots will tell us where to grow.\nLeave room for me, I'll leave you room,\nA hundred colors, one small bloom.\n\nWe hung the canvas where the shadows fell,\nNot every mark had everything to tell.\nSome held the road, some only held the rain,\nTogether they could make a world feel plain.\n\nThe loudest bell stepped back to hear a bird,\nA simple note was suddenly a word.\nWe did not need to sound the same to sing,\nThe open space could hold a different wing.\n\nCome as you are, bring what you know,\nThe quiet roots will tell us where to grow.\nLeave room for me, I'll leave you room,\nA hundred colors, one small bloom.\n\nAnd when the room grew still enough to sleep,\nWe knew which little marks we meant to keep.\nThe picture stayed unfinished by the door,\nWith room for what tomorrow might be for.",
"instrumental": false,
"vocal_language": "en",
"bpm": 86,
"keyscale": "G major",
"timesignature": "4",
"duration": 120,
"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": 202611070101,
"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 chamber pop in4/4 at86BPM,Gmajor. Verse G–C–Em–D; chorus C–G–Am–D with final G. Guitar/piano leave gaps for vocal clarity, strings answer rather than double. This is an arrangement plan, not verified rendered notes/chords or exact transcript.
VERIFIED TECHNICAL OUTPUT
{
"requested_seconds": 120,
"lyrics_characters": 1183,
"lyrics_tokens": 281,
"seconds": 120.0,
"sample_rate": 48000,
"channels": 2,
"peak": 0.891265869140625,
"rms": 0.1587654918249353,
"finite": true,
"generation_seconds": 316.564240694046,
"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": "120.000000"
}
},
"m4a_sha256": "6716b209ea606337a09bc1a007a71cfa31c7696ee15da590cb631560bd1a9dbc"
}
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.
AUTOMATED WORD CHECK
Local Whisper base.en processed the full120-second track. It recovered several opening, chorus and closing phrases, with omissions and substitutions. This flags uncertain lyric fidelity; it is not an exact verified transcript or full listening review.
No comments yet. Start the conversation.