Scylla's Band v4-20261106: speech and singing from one model (a delivery mode on the flow, a BigVGAN singing decoder); LiteRT, ONNX, WebGPU, Core ML, Core AI and PyTorch
b0fe862 verified {
"architecture": "scyllasband-duration-flow",
"assets": {
"fixed_delivery_references": "assets/fixed_references.json",
"g2p_config": "assets/g2p/export_config.json",
"g2p_language_map": "assets/g2p/language_map.json",
"g2p_normalization": "assets/g2p/normalization.json",
"g2p_phoneme_dict": "assets/g2p/phoneme_dict.json",
"g2p_pronunciation_overrides": "assets/g2p/pronunciation_overrides.json",
"g2p_tokenizer": "assets/g2p/tokenizer.json",
"language_index": "assets/languages.json",
"phone_vocab": "assets/phone_vocab.json",
"voice_index": "assets/voices.json"
},
"audio": {
"hop_length": 256,
"latent_dim": 24,
"latent_hop_length": 512,
"n_mels": 100,
"sample_rate": 24000
},
"components": {
"g2p_64": {
"artifacts": {
"coreml": {
"format": "coreml",
"path": "coreml/g2p.mlmodelc",
"function": "g2p_64"
}
},
"inputs": [
"text"
],
"outputs": [
"logits"
],
"required": false
},
"g2p_128": {
"artifacts": {
"coreml": {
"format": "coreml",
"path": "coreml/g2p.mlmodelc",
"function": "g2p_128"
}
},
"inputs": [
"text"
],
"outputs": [
"logits"
],
"required": false
},
"g2p_256": {
"artifacts": {
"coreml": {
"format": "coreml",
"path": "coreml/g2p.mlmodelc",
"function": "g2p_256"
}
},
"inputs": [
"text"
],
"outputs": [
"logits"
],
"required": false
},
"g2p": {
"artifacts": {
"coreml": {
"format": "coreml",
"path": "coreml/g2p.mlmodelc",
"function": "g2p"
}
},
"inputs": [
"text"
],
"outputs": [
"logits"
],
"required": true
},
"duration_predictor": {
"artifacts": {
"coreml": {
"format": "coreml",
"path": "coreml/duration_predictor.mlmodelc"
}
},
"inputs": [
"span_phone_ids",
"span_segment_ids",
"span_mask",
"voice_id",
"language_id",
"delivery_values",
"delivery_present"
],
"outputs": [
"durations"
],
"required": true
},
"vector_context_encoder": {
"artifacts": {
"coreml": {
"format": "coreml",
"path": "coreml/vector_context_encoder.mlmodelc"
}
},
"inputs": [
"span_context_phone_ids",
"span_context_segment_ids",
"span_context_mask"
],
"outputs": [
"span_context_hidden"
],
"required": true
},
"pitch_context_encoder": {
"artifacts": {
"coreml": {
"format": "coreml",
"path": "coreml/pitch_context_encoder.mlmodelc"
}
},
"inputs": [
"span_context_phone_ids",
"span_context_segment_ids",
"span_context_mask"
],
"outputs": [
"span_context_hidden"
],
"required": true
},
"vector_estimator_128": {
"artifacts": {
"coreml": {
"format": "coreml",
"path": "coreml/vector_estimator.mlmodelc",
"function": "vector_estimator_128"
}
},
"inputs": [
"noise",
"time",
"expanded_phone_ids",
"voice_id",
"language_id",
"delivery_values",
"delivery_present",
"latent_mask",
"span_context_hidden",
"prefix_latents",
"prefix_mask",
"expanded_boundary_event_ids",
"expanded_modifier_event_ids",
"expanded_phone_phase",
"expanded_phone_log_duration",
"expanded_sentence_type_ids",
"expanded_melody",
"delivery_mode_id"
],
"outputs": [
"velocity"
],
"required": false
},
"pitch_estimator_128": {
"artifacts": {
"coreml": {
"format": "coreml",
"path": "coreml/pitch_estimator.mlmodelc",
"function": "pitch_estimator_128"
}
},
"inputs": [
"noise",
"time",
"expanded_phone_ids",
"voice_id",
"language_id",
"delivery_values",
"delivery_present",
"latent_mask",
"span_context_hidden",
"expanded_boundary_event_ids",
"expanded_modifier_event_ids",
"expanded_phone_phase",
"expanded_phone_log_duration",
"expanded_sentence_type_ids"
],
"outputs": [
"velocity"
],
"required": false
},
"vocoder_128": {
"artifacts": {
"coreml": {
"format": "coreml",
"path": "coreml/vocoder.mlmodelc",
"function": "vocoder_128"
}
},
"inputs": [
"latents",
"latent_mask",
"voice_id",
"language_id",
"emotion_id"
],
"outputs": [
"audio"
],
"required": false
},
"vocoder_bigvgan_128": {
"artifacts": {
"coreml": {
"format": "coreml",
"path": "coreml/vocoder_bigvgan.mlmodelc",
"function": "vocoder_bigvgan_128"
}
},
"inputs": [
"latents",
"latent_mask",
"voice_id",
"language_id",
"emotion_id"
],
"outputs": [
"audio"
],
"required": false
},
"vector_estimator_256": {
"artifacts": {
"coreml": {
"format": "coreml",
"path": "coreml/vector_estimator.mlmodelc",
"function": "vector_estimator_256"
}
},
"inputs": [
"noise",
"time",
"expanded_phone_ids",
"voice_id",
"language_id",
"delivery_values",
"delivery_present",
"latent_mask",
"span_context_hidden",
"prefix_latents",
"prefix_mask",
"expanded_boundary_event_ids",
"expanded_modifier_event_ids",
"expanded_phone_phase",
"expanded_phone_log_duration",
"expanded_sentence_type_ids",
"expanded_melody",
"delivery_mode_id"
],
"outputs": [
"velocity"
],
"required": false
},
"pitch_estimator_256": {
"artifacts": {
"coreml": {
"format": "coreml",
"path": "coreml/pitch_estimator.mlmodelc",
"function": "pitch_estimator_256"
}
},
"inputs": [
"noise",
"time",
"expanded_phone_ids",
"voice_id",
"language_id",
"delivery_values",
"delivery_present",
"latent_mask",
"span_context_hidden",
"expanded_boundary_event_ids",
"expanded_modifier_event_ids",
"expanded_phone_phase",
"expanded_phone_log_duration",
"expanded_sentence_type_ids"
],
"outputs": [
"velocity"
],
"required": false
},
"vocoder_256": {
"artifacts": {
"coreml": {
"format": "coreml",
"path": "coreml/vocoder.mlmodelc",
"function": "vocoder_256"
}
},
"inputs": [
"latents",
"latent_mask",
"voice_id",
"language_id",
"emotion_id"
],
"outputs": [
"audio"
],
"required": false
},
"vocoder_bigvgan_256": {
"artifacts": {
"coreml": {
"format": "coreml",
"path": "coreml/vocoder_bigvgan.mlmodelc",
"function": "vocoder_bigvgan_256"
}
},
"inputs": [
"latents",
"latent_mask",
"voice_id",
"language_id",
"emotion_id"
],
"outputs": [
"audio"
],
"required": false
},
"vector_estimator_384": {
"artifacts": {
"coreml": {
"format": "coreml",
"path": "coreml/vector_estimator.mlmodelc",
"function": "vector_estimator_384"
}
},
"inputs": [
"noise",
"time",
"expanded_phone_ids",
"voice_id",
"language_id",
"delivery_values",
"delivery_present",
"latent_mask",
"span_context_hidden",
"prefix_latents",
"prefix_mask",
"expanded_boundary_event_ids",
"expanded_modifier_event_ids",
"expanded_phone_phase",
"expanded_phone_log_duration",
"expanded_sentence_type_ids",
"expanded_melody",
"delivery_mode_id"
],
"outputs": [
"velocity"
],
"required": false
},
"pitch_estimator_384": {
"artifacts": {
"coreml": {
"format": "coreml",
"path": "coreml/pitch_estimator.mlmodelc",
"function": "pitch_estimator_384"
}
},
"inputs": [
"noise",
"time",
"expanded_phone_ids",
"voice_id",
"language_id",
"delivery_values",
"delivery_present",
"latent_mask",
"span_context_hidden",
"expanded_boundary_event_ids",
"expanded_modifier_event_ids",
"expanded_phone_phase",
"expanded_phone_log_duration",
"expanded_sentence_type_ids"
],
"outputs": [
"velocity"
],
"required": false
},
"vocoder_384": {
"artifacts": {
"coreml": {
"format": "coreml",
"path": "coreml/vocoder.mlmodelc",
"function": "vocoder_384"
}
},
"inputs": [
"latents",
"latent_mask",
"voice_id",
"language_id",
"emotion_id"
],
"outputs": [
"audio"
],
"required": false
},
"vocoder_bigvgan_384": {
"artifacts": {
"coreml": {
"format": "coreml",
"path": "coreml/vocoder_bigvgan.mlmodelc",
"function": "vocoder_bigvgan_384"
}
},
"inputs": [
"latents",
"latent_mask",
"voice_id",
"language_id",
"emotion_id"
],
"outputs": [
"audio"
],
"required": false
},
"vector_estimator_512": {
"artifacts": {
"coreml": {
"format": "coreml",
"path": "coreml/vector_estimator.mlmodelc",
"function": "vector_estimator_512"
}
},
"inputs": [
"noise",
"time",
"expanded_phone_ids",
"voice_id",
"language_id",
"delivery_values",
"delivery_present",
"latent_mask",
"span_context_hidden",
"prefix_latents",
"prefix_mask",
"expanded_boundary_event_ids",
"expanded_modifier_event_ids",
"expanded_phone_phase",
"expanded_phone_log_duration",
"expanded_sentence_type_ids",
"expanded_melody",
"delivery_mode_id"
],
"outputs": [
"velocity"
],
"required": false
},
"pitch_estimator_512": {
"artifacts": {
"coreml": {
"format": "coreml",
"path": "coreml/pitch_estimator.mlmodelc",
"function": "pitch_estimator_512"
}
},
"inputs": [
"noise",
"time",
"expanded_phone_ids",
"voice_id",
"language_id",
"delivery_values",
"delivery_present",
"latent_mask",
"span_context_hidden",
"expanded_boundary_event_ids",
"expanded_modifier_event_ids",
"expanded_phone_phase",
"expanded_phone_log_duration",
"expanded_sentence_type_ids"
],
"outputs": [
"velocity"
],
"required": false
},
"vocoder_512": {
"artifacts": {
"coreml": {
"format": "coreml",
"path": "coreml/vocoder.mlmodelc",
"function": "vocoder_512"
}
},
"inputs": [
"latents",
"latent_mask",
"voice_id",
"language_id",
"emotion_id"
],
"outputs": [
"audio"
],
"required": false
},
"vocoder_bigvgan_512": {
"artifacts": {
"coreml": {
"format": "coreml",
"path": "coreml/vocoder_bigvgan.mlmodelc",
"function": "vocoder_bigvgan_512"
}
},
"inputs": [
"latents",
"latent_mask",
"voice_id",
"language_id",
"emotion_id"
],
"outputs": [
"audio"
],
"required": false
},
"vector_estimator_768": {
"artifacts": {
"coreml": {
"format": "coreml",
"path": "coreml/vector_estimator.mlmodelc",
"function": "vector_estimator_768"
}
},
"inputs": [
"noise",
"time",
"expanded_phone_ids",
"voice_id",
"language_id",
"delivery_values",
"delivery_present",
"latent_mask",
"span_context_hidden",
"prefix_latents",
"prefix_mask",
"expanded_boundary_event_ids",
"expanded_modifier_event_ids",
"expanded_phone_phase",
"expanded_phone_log_duration",
"expanded_sentence_type_ids",
"expanded_melody",
"delivery_mode_id"
],
"outputs": [
"velocity"
],
"required": false
},
"pitch_estimator_768": {
"artifacts": {
"coreml": {
"format": "coreml",
"path": "coreml/pitch_estimator.mlmodelc",
"function": "pitch_estimator_768"
}
},
"inputs": [
"noise",
"time",
"expanded_phone_ids",
"voice_id",
"language_id",
"delivery_values",
"delivery_present",
"latent_mask",
"span_context_hidden",
"expanded_boundary_event_ids",
"expanded_modifier_event_ids",
"expanded_phone_phase",
"expanded_phone_log_duration",
"expanded_sentence_type_ids"
],
"outputs": [
"velocity"
],
"required": false
},
"vocoder_768": {
"artifacts": {
"coreml": {
"format": "coreml",
"path": "coreml/vocoder.mlmodelc",
"function": "vocoder_768"
}
},
"inputs": [
"latents",
"latent_mask",
"voice_id",
"language_id",
"emotion_id"
],
"outputs": [
"audio"
],
"required": false
},
"vector_estimator": {
"artifacts": {
"coreml": {
"format": "coreml",
"path": "coreml/vector_estimator.mlmodelc",
"function": "vector_estimator"
}
},
"inputs": [
"noise",
"time",
"expanded_phone_ids",
"voice_id",
"language_id",
"delivery_values",
"delivery_present",
"latent_mask",
"span_context_hidden",
"prefix_latents",
"prefix_mask",
"expanded_boundary_event_ids",
"expanded_modifier_event_ids",
"expanded_phone_phase",
"expanded_phone_log_duration",
"expanded_sentence_type_ids",
"expanded_melody",
"delivery_mode_id"
],
"outputs": [
"velocity"
],
"required": true
},
"pitch_estimator": {
"artifacts": {
"coreml": {
"format": "coreml",
"path": "coreml/pitch_estimator.mlmodelc",
"function": "pitch_estimator"
}
},
"inputs": [
"noise",
"time",
"expanded_phone_ids",
"voice_id",
"language_id",
"delivery_values",
"delivery_present",
"latent_mask",
"span_context_hidden",
"expanded_boundary_event_ids",
"expanded_modifier_event_ids",
"expanded_phone_phase",
"expanded_phone_log_duration",
"expanded_sentence_type_ids"
],
"outputs": [
"velocity"
],
"required": true
},
"vocoder": {
"artifacts": {
"coreml": {
"format": "coreml",
"path": "coreml/vocoder.mlmodelc",
"function": "vocoder"
}
},
"inputs": [
"latents",
"latent_mask",
"voice_id",
"language_id",
"emotion_id"
],
"outputs": [
"audio"
],
"required": true
}
},
"contract_version": "1.0.0",
"controls": {
"chunk_context": {
"artificial_continuation_boundaries": [
"chunk_continue"
],
"artificial_continuation_phone": null,
"boundary_after_values": [
"sentence_end",
"paragraph_end",
"clause_continue",
"chunk_continue"
],
"boundary_before_values": [
"sentence_start",
"paragraph_start",
"clause_continue",
"chunk_continue"
],
"clause_continuation_fallback_phone": "<pause_comma>",
"conditioning": "boundary_embeddings",
"context_phone_tokens": {
"continuation": "<ctx_continuation>",
"sentence_end": "<ctx_sentence_end>",
"sentence_start": "<ctx_sentence_start>"
},
"default_boundary_after": "sentence_end",
"default_boundary_before": "sentence_start",
"emit_context_phone_tokens": false,
"linguistic_continuation_boundaries": [
"clause_continue"
],
"schema_version": 2
},
"chunking": {
"shared_split_phone": "<sil>",
"split_after": [
"<end_stmt>",
"<end_question>",
"<end_exclaim>",
"<ellipsis>"
],
"unit": "sentence"
},
"decoders": {
"bigvgan": {
"component": "vocoder_bigvgan",
"license": "BigVGAN v2 (NVIDIA, MIT) fine-tuned",
"output_samples": "latent_frames * 512",
"required": false,
"samples_per_frame": 512
},
"vocos": {
"component": "vocoder",
"output_samples": "latent_frames * 512 - 256",
"samples_per_frame": 512
}
},
"decoding": {
"context_frames": 48,
"mode": "overlap"
},
"delivery": {
"defaults": {
"ariadne": {
"intensity": 0.0,
"pace": 0.0,
"pitch": 0.0
},
"felix": {
"intensity": 0.0,
"pace": 0.0,
"pitch": 0.0
},
"gwen": {
"intensity": 0.0,
"pace": 0.0,
"pitch": 0.0
},
"ink": {
"intensity": 0.0,
"pace": 0.0,
"pitch": 0.0
},
"kincade": {
"intensity": 0.0,
"pace": 0.0,
"pitch": 0.0
},
"max": {
"intensity": 0.0,
"pace": 0.0,
"pitch": 0.0
},
"orpheus": {
"intensity": 0.0,
"pace": 0.0,
"pitch": 0.0
},
"poppy": {
"intensity": 0.0,
"pace": 0.0,
"pitch": 0.0
},
"priya": {
"intensity": 0.0,
"pace": 0.0,
"pitch": 0.0
},
"rex": {
"intensity": 0.0,
"pace": 0.0,
"pitch": 0.0
},
"scylla": {
"intensity": 0.0,
"pace": 0.0,
"pitch": 0.0
},
"stone": {
"intensity": 0.0,
"pace": 0.0,
"pitch": 0.0
},
"thistle": {
"intensity": 0.0,
"pace": 0.0,
"pitch": 0.0
},
"tuesday": {
"intensity": 0.0,
"pace": 0.0,
"pitch": 0.0
}
},
"graph_slots": 5,
"min_spoken_phones": 4,
"ranges": {
"intensity": [
-2.0,
2.0
],
"pace": [
-2.0,
2.0
],
"pitch": [
-2.0,
2.0
]
},
"release_id": "v4-20261106",
"rule": "value = clip(z, -z_limit, z_limit) / z_scale, present; both slots absent on a target with fewer than min_spoken_phones spoken phones; slots 2-4 always absent",
"schema": "measured_controls_v1",
"slots": [
"intensity",
"pace"
],
"units": {
"intensity": "sd",
"pace": "sd",
"pitch": "semitones"
},
"voice_locales": {
"ariadne": [
"de",
"en_us",
"es",
"fr",
"it",
"vi"
],
"felix": [
"de",
"en_us",
"es",
"fr",
"it",
"vi"
],
"gwen": [
"de",
"en_us",
"es",
"fr",
"it",
"vi"
],
"ink": [
"de",
"en_gb",
"es",
"fr",
"it",
"vi"
],
"kincade": [
"en_us",
"es",
"de",
"fr",
"it",
"vi"
],
"max": [
"de",
"en_us",
"es",
"fr",
"it",
"vi"
],
"orpheus": [
"de",
"en_gb",
"es",
"fr",
"it",
"vi"
],
"poppy": [
"en_us",
"es",
"de",
"fr",
"it",
"vi"
],
"priya": [
"en_us",
"es",
"de",
"fr",
"it",
"vi"
],
"rex": [
"de",
"en_us",
"es",
"fr",
"it",
"vi"
],
"scylla": [
"de",
"en_us",
"es",
"fr",
"it",
"vi"
],
"stone": [
"de",
"en_us",
"es",
"fr",
"it",
"vi"
],
"thistle": [
"en_us",
"es",
"de",
"fr",
"it",
"vi"
],
"tuesday": [
"de",
"en_gb",
"es",
"fr",
"it",
"vi"
]
},
"z_limit": 2.5,
"z_scale": 5.0
},
"delivery_modes": {
"default": "spoken",
"enabled": true,
"ids": {
"ballad": 3,
"rap": 2,
"spoken": 0,
"sung": 1
},
"input": "delivery_mode_id",
"singing": {
"decoder": "bigvgan",
"guidance": 1.0,
"melody": {
"layout": "note_phase_presence",
"midi_center": 60,
"midi_scale": 24,
"rule": "per frame: ((midi - midi_center) / midi_scale, phase 0..1 inside the note, 1 where a note sounds); zeros on rests"
},
"modes": [
"sung",
"ballad"
],
"pitch_predictor": "bypassed",
"pitch_soft_limit": "bypassed",
"rule": "sung and ballad targets take their melody from the score (expanded_melody in the note_phase_presence layout), skip the pitch predictor and the pitch soft limit, and render with the singing sampler and steps; spoken targets are unchanged from v3",
"sampler": "euler",
"steps": 4,
"voice_midi_center": {
"ariadne": 59.0,
"felix": 50.0,
"gwen": 56.0,
"ink": 57.0,
"kincade": 49.0,
"max": 49.0,
"orpheus": 50.0,
"poppy": 58.0,
"priya": 58.0,
"rex": 49.0,
"scylla": 59.0,
"stone": 49.0,
"thistle": 59.0,
"tuesday": 58.0
}
}
},
"durations": {
"rounding": "half_even",
"silence_min_frames": 0,
"speech_min_frames": 1,
"zero_frame_phones": "punctuation_and_modifiers"
},
"emotions": {
"enabled": false
},
"energy": {
"default": 1.0,
"max": 1.5,
"min": 0.5
},
"fixed_shapes": {
"g2p_text_tokens": 512,
"latent_frames": 1024,
"phone_frames": 512
},
"g2p_buckets": [
{
"text_tokens": 64,
"component": "g2p_64"
},
{
"text_tokens": 128,
"component": "g2p_128"
},
{
"text_tokens": 256,
"component": "g2p_256"
},
{
"text_tokens": 512,
"component": "g2p"
}
],
"graph_input_contract": "scyllasband_measured_controls_v4",
"pace_pauses": {
"per_sd": -0.13,
"phone": "<sil>",
"rule": "before rounding, each <sil> position's predicted frames are multiplied by exp(per_sd * pace)"
},
"pitch": {
"center": 10.0,
"channels": 2,
"context_encoder": "pitch_context_encoder",
"edges": {
"ariadne": [
7.69,
27.31
],
"felix": [
-3.02,
18.91
],
"gwen": [
4.84,
25.68
],
"ink": [
3.83,
24.19
],
"kincade": [
-6.17,
18.61
],
"max": [
-9.9,
17.2
],
"orpheus": [
-4.35,
18.42
],
"poppy": [
6.97,
25.88
],
"priya": [
6.0,
25.96
],
"rex": [
-3.75,
17.13
],
"scylla": [
8.47,
28.12
],
"stone": [
-7.92,
17.8
],
"thistle": [
6.5,
26.67
],
"tuesday": [
6.13,
24.86
]
},
"knee": 2.0,
"melody_center": 16.65,
"melody_scale": 24.0,
"rule": "contour [2, T]: st = c0 * scale + center + shift; st soft-limited inside the voice's edges (knee = min(knee, (high - low) / 4): unchanged until knee semitones from an edge, then edge -/+ knee * tanh); p = clip((c1 + 1) / 2, 0, 1); voiced = p > voiced_threshold; melody [T, 3] = ((st - melody_center) / melody_scale * voiced, p, voiced)",
"sampler": {
"choices": [
"euler",
"heun"
],
"default": "euler"
},
"scale": 6.0,
"steps": {
"default": 4,
"max": 64,
"min": 1
},
"voiced_threshold": 0.5
},
"prefix_conditioning": {
"alignment": "right",
"enabled": true,
"max_frames": 96,
"source": "previous_latents_tail"
},
"punctuation_silence": {
"calibrated_floors": false,
"floor_table_ms": {},
"silence_phone": "<sil>",
"target": "explicit_silence"
},
"reference_packs": {
"enabled": false,
"fixed_in_graph": true
},
"sampler": {
"choices": [
"euler",
"heun"
],
"default": "euler"
},
"span_conditioning": {
"context_max_phones": 512,
"context_phones_each_side": 180,
"duration_inputs": [
"span_phone_ids",
"span_segment_ids",
"span_mask"
],
"enabled": true,
"encoder_component": "vector_context_encoder",
"encoder_inputs": [
"span_context_phone_ids",
"span_context_segment_ids",
"span_context_mask"
],
"exclude_context_phones": [
"<sil>"
],
"hidden_size": 512,
"layout": "balanced_before_target_after",
"pitch_hidden_size": 384,
"scope": "passage",
"segments": 3,
"solver_input": "span_context_hidden"
},
"speed": {
"default": 1.0,
"max": 1.25,
"min": 0.75
},
"steps": {
"default": 4,
"max": 64,
"min": 1
},
"target_buckets": {
"bucket_margin_frames": 0,
"buckets": [
{
"default": false,
"latent_frames": 128,
"vector_estimator": "vector_estimator_128",
"pitch_estimator": "pitch_estimator_128",
"vocoder": "vocoder_128",
"vocoder_bigvgan": "vocoder_bigvgan_128"
},
{
"default": false,
"latent_frames": 256,
"vector_estimator": "vector_estimator_256",
"pitch_estimator": "pitch_estimator_256",
"vocoder": "vocoder_256",
"vocoder_bigvgan": "vocoder_bigvgan_256"
},
{
"default": false,
"latent_frames": 384,
"vector_estimator": "vector_estimator_384",
"pitch_estimator": "pitch_estimator_384",
"vocoder": "vocoder_384",
"vocoder_bigvgan": "vocoder_bigvgan_384"
},
{
"default": false,
"latent_frames": 512,
"vector_estimator": "vector_estimator_512",
"pitch_estimator": "pitch_estimator_512",
"vocoder": "vocoder_512",
"vocoder_bigvgan": "vocoder_bigvgan_512"
},
{
"default": false,
"latent_frames": 768,
"vector_estimator": "vector_estimator_768",
"pitch_estimator": "pitch_estimator_768",
"vocoder": "vocoder_768"
},
{
"default": true,
"latent_frames": 1024,
"vector_estimator": "vector_estimator",
"pitch_estimator": "pitch_estimator",
"vocoder": "vocoder"
}
],
"default_latent_frames": 1024,
"enabled": true,
"policy": "smallest_fit"
},
"text_normalizer": {
"prepared_contract_recorded": true,
"sha256": "d8fd1b2415d0d100d1c70237a4469117ee6b73d0e4da703e4654c83192779cc4",
"version": "scyllasband_spoken_text_v2_2026_08_05"
},
"timing_events": {
"enabled": true,
"inputs": [
"expanded_boundary_event_ids",
"expanded_modifier_event_ids",
"expanded_phone_phase",
"expanded_phone_log_duration",
"expanded_sentence_type_ids"
],
"modifier_bits": {
"ˈ": 1,
"ˌ": 2,
"ː": 4,
"̃": 8,
"̩": 16,
"̪": 32
},
"punctuation_owner": "following_silence_else_first_frame_of_next_phone",
"sentence_type_count": 5,
"sentence_type_lookahead": "following_context",
"sentence_types": {
"<ellipsis>": 4,
"<end_exclaim>": 3,
"<end_question>": 2,
"<end_stmt>": 1
},
"word_start_event_id": 87,
"word_start_owner": "first_phone_of_word_after_chunk_first_word"
},
"word_boundaries": {
"duration_phone": "<sil>",
"enabled": true,
"g2p_output_symbol": " ",
"zero_frames_allowed": true
},
"coreml": {
"minimum_os": {
"ios": "18.0",
"macos": "15.0"
},
"io": {
"ids": "int32",
"masks": "int32",
"values": "float32"
},
"assets": {
"g2p": {
"precision": "fp16",
"weights": "w8",
"bytes": 27735781
},
"duration_predictor": {
"precision": "fp16",
"weights": "w8",
"bytes": 10720880
},
"vector_context_encoder": {
"precision": "fp16",
"weights": "w8",
"bytes": 7617880
},
"pitch_context_encoder": {
"precision": "fp16",
"weights": "w8",
"bytes": 4398800
},
"pitch_estimator": {
"precision": "fp16",
"weights": "w8",
"bytes": 24970951
},
"vector_estimator": {
"precision": "fp16",
"weights": "w8",
"bytes": 62271199
},
"vocoder": {
"precision": "fp16",
"weights": "w8",
"bytes": 32013114
},
"vocoder_bigvgan": {
"precision": "fp16",
"weights": "none",
"bytes": 254496556
}
},
"compute_units": "gpu",
"neural_engine_assets": [],
"compute_units_ios": "gpu,vocoder_bigvgan=cpu"
}
},
"dataset_summary": {
"controls": "measured_controls_v1",
"voice_locale_pairs": 84
},
"default_language": "en_us",
"languages": [
"en_us",
"en_gb",
"es",
"it",
"fr",
"de",
"vi"
],
"model_name": "Scylla's Band",
"model_version": "3",
"preferred_backends": [
"coreml"
],
"voices": [
{
"default_language": "en_us",
"embedding_path": null,
"id": "ariadne",
"languages": [
"de",
"en_us",
"es",
"fr",
"it",
"vi"
],
"name": "ariadne",
"styles": [
"default"
]
},
{
"default_language": "en_us",
"embedding_path": null,
"id": "felix",
"languages": [
"de",
"en_us",
"es",
"fr",
"it",
"vi"
],
"name": "felix",
"styles": [
"default"
]
},
{
"default_language": "en_us",
"embedding_path": null,
"id": "gwen",
"languages": [
"de",
"en_us",
"es",
"fr",
"it",
"vi"
],
"name": "gwen",
"styles": [
"default"
]
},
{
"default_language": "en_gb",
"embedding_path": null,
"id": "ink",
"languages": [
"de",
"en_gb",
"es",
"fr",
"it",
"vi"
],
"name": "ink",
"styles": [
"default"
]
},
{
"default_language": "en_us",
"embedding_path": null,
"id": "max",
"languages": [
"de",
"en_us",
"es",
"fr",
"it",
"vi"
],
"name": "max",
"styles": [
"default"
]
},
{
"default_language": "en_gb",
"embedding_path": null,
"id": "orpheus",
"languages": [
"de",
"en_gb",
"es",
"fr",
"it",
"vi"
],
"name": "orpheus",
"styles": [
"default"
]
},
{
"default_language": "en_us",
"embedding_path": null,
"id": "rex",
"languages": [
"de",
"en_us",
"es",
"fr",
"it",
"vi"
],
"name": "rex",
"styles": [
"default"
]
},
{
"default_language": "en_us",
"embedding_path": null,
"id": "scylla",
"languages": [
"de",
"en_us",
"es",
"fr",
"it",
"vi"
],
"name": "scylla",
"styles": [
"default"
]
},
{
"default_language": "en_us",
"embedding_path": null,
"id": "stone",
"languages": [
"de",
"en_us",
"es",
"fr",
"it",
"vi"
],
"name": "stone",
"styles": [
"default"
]
},
{
"default_language": "en_gb",
"embedding_path": null,
"id": "tuesday",
"languages": [
"de",
"en_gb",
"es",
"fr",
"it",
"vi"
],
"name": "tuesday",
"styles": [
"default"
]
},
{
"default_language": "en_us",
"embedding_path": null,
"id": "thistle",
"languages": [
"en_us",
"es",
"de",
"fr",
"it",
"vi"
],
"name": "thistle",
"styles": [
"default"
]
},
{
"default_language": "en_us",
"embedding_path": null,
"id": "kincade",
"languages": [
"en_us",
"es",
"de",
"fr",
"it",
"vi"
],
"name": "kincade",
"styles": [
"default"
]
},
{
"default_language": "en_us",
"embedding_path": null,
"id": "poppy",
"languages": [
"en_us",
"es",
"de",
"fr",
"it",
"vi"
],
"name": "poppy",
"styles": [
"default"
]
},
{
"default_language": "en_us",
"embedding_path": null,
"id": "priya",
"languages": [
"en_us",
"es",
"de",
"fr",
"it",
"vi"
],
"name": "priya",
"styles": [
"default"
]
}
]
}
{
"architecture": "scyllasband-duration-flow",
"assets": {
"fixed_delivery_references": "assets/fixed_references.json",
"g2p_config": "assets/g2p/export_config.json",
"g2p_language_map": "assets/g2p/language_map.json",
"g2p_normalization": "assets/g2p/normalization.json",
"g2p_phoneme_dict": "assets/g2p/phoneme_dict.json",
"g2p_pronunciation_overrides": "assets/g2p/pronunciation_overrides.json",
"g2p_tokenizer": "assets/g2p/tokenizer.json",
"language_index": "assets/languages.json",
"phone_vocab": "assets/phone_vocab.json",
"voice_index": "assets/voices.json"
},
"audio": {
"hop_length": 256,
"latent_dim": 24,
"latent_hop_length": 512,
"n_mels": 100,
"sample_rate": 24000
},
"components": {
"g2p_64": {
"artifacts": {
"coreml": {
"format": "coreml",
"path": "coreml/g2p.mlmodelc",
"function": "g2p_64"
}
},
"inputs": [
"text"
],
"outputs": [
"logits"
],
"required": false
},
"g2p_128": {
"artifacts": {
"coreml": {
"format": "coreml",
"path": "coreml/g2p.mlmodelc",
"function": "g2p_128"
}
},
"inputs": [
"text"
],
"outputs": [
"logits"
],
"required": false
},
"g2p_256": {
"artifacts": {
"coreml": {
"format": "coreml",
"path": "coreml/g2p.mlmodelc",
"function": "g2p_256"
}
},
"inputs": [
"text"
],
"outputs": [
"logits"
],
"required": false
},
"g2p": {
"artifacts": {
"coreml": {
"format": "coreml",
"path": "coreml/g2p.mlmodelc",
"function": "g2p"
}
},
"inputs": [
"text"
],
"outputs": [
"logits"
],
"required": true
},
"duration_predictor": {
"artifacts": {
"coreml": {
"format": "coreml",
"path": "coreml/duration_predictor.mlmodelc"
}
},
"inputs": [
"span_phone_ids",
"span_segment_ids",
"span_mask",
"voice_id",
"language_id",
"delivery_values",