vox-models / models_manifest.json
addy-hypr4
updated manifest json
6399a1a
Raw
History Blame Contribute Delete
9.27 kB
{
"models_version": "1.1.0",
"release_notes": [
"Portable, single-instance TTS engine with 31 languages and flow-matching architecture.",
"Supertonic 3 replaces Kokoro (EN) + Piper (HI) as the sole TTS engine.",
"Chatterbox TTS integrated"
],
"total_size_bytes": 9398491074,
"model_groups": [
{
"id": "ten_vad",
"name": "Ten VAD Engine",
"category": "vad",
"version": "1.0.0",
"files": [
{
"id": "ten_vad_onnx",
"path": "vad/ten_vad.onnx",
"size": 332211,
"sha256": "718cb7eef47e3cf5ddbe7e967a7503f46b8b469c0706872f494dfa921b486206",
"required": true
}
]
},
{
"id": "vox_translit_rnn",
"name": "Vox Transliteration Engine",
"category": "translit",
"version": "1.0.0",
"files": [
{
"id": "translit_encoder",
"path": "translit/encoder.onnx",
"size": 9529392,
"sha256": "af1ed31d5af319a353587c746b5c7540646e154d977d7614081c30f8bfb40564",
"required": true
},
{
"id": "translit_decoder",
"path": "translit/decoder.onnx",
"size": 6819685,
"sha256": "4930f3460baf4c0f75a346e1320579469b4ff5e00d3e62375cbcb0cee5120aa3",
"required": true
},
{
"id": "translit_input_vocab",
"path": "translit/input_vocab.json",
"size": 1395,
"sha256": "b7126832254c449c9a208ec650feae5682a7f77323fd2e9bf2ad29c1ab7332e2",
"required": true
},
{
"id": "translit_target_vocab",
"path": "translit/target_vocab.json",
"size": 787,
"sha256": "bd5e364110187e05fcbf00529af0facf45a7838e2aa6b410390af1d80ff08f96",
"required": true
}
]
},
{
"id": "nvidia_nemotron",
"name": "Nemotron-3.5 ASR Engine",
"category": "stt",
"version": "1.0.0",
"files": [
{
"id": "stt_nemotron_config",
"path": "stt/nvidia-nemotron-3.5/config.json",
"size": 602,
"sha256": "0592a224f30670e00f5e0f1f106f0171428b0abde0fd4cbc64237b02c2241502",
"required": true
},
{
"id": "stt_nemotron_decoder_joint",
"path": "stt/nvidia-nemotron-3.5/decoder_joint.onnx",
"size": 97590054,
"sha256": "634dfadf24cb4f73c2fae170b36611d68db48186426882cbc8f7e02ed9f2bb29",
"required": true
},
{
"id": "stt_nemotron_encoder",
"path": "stt/nvidia-nemotron-3.5/encoder.onnx",
"size": 657572215,
"sha256": "e653d494a4855ee87f6251e8a9677416a73edf6f36578841316fa2b77a53cda7",
"required": true
},
{
"id": "stt_nemotron_tokenizer",
"path": "stt/nvidia-nemotron-3.5/tokenizer.model",
"size": 406554,
"sha256": "ce3895e40806f02a26c3a225161b96ef682d6c0054bae32a245dec4258d7d291",
"required": true
}
]
},
{
"id": "qwen3_asr",
"name": "Qwen3 ASR Engine",
"category": "stt",
"version": "1.0.0",
"files": [
{
"id": "stt_conv_frontend",
"path": "stt/qwen3-asr/conv_frontend.onnx",
"size": 44148281,
"sha256": "1f38b879b0871c9f689b092ad4fa85c68ef473c585dcf53d50a029fe8a0ab0cb",
"required": false
},
{
"id": "stt_encoder",
"path": "stt/qwen3-asr/encoder.int8.onnx",
"size": 182491662,
"sha256": "ae0cf814d9cd5249b98a1aa9199511d0c0a0c5c8b3059532637fa3cb4785c60c",
"required": false
},
{
"id": "stt_decoder",
"path": "stt/qwen3-asr/decoder.int8.onnx",
"size": 755913551,
"sha256": "768f0cc54a804e5b9724133910071995ce03ecd1a4d5be8e5e766b022623dc8d",
"required": false
},
{
"id": "stt_vocab",
"path": "stt/qwen3-asr/tokenizer/vocab.json",
"size": 2776833,
"sha256": "ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910",
"required": false
},
{
"id": "stt_merges",
"path": "stt/qwen3-asr/tokenizer/merges.txt",
"size": 1671853,
"sha256": "8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5",
"required": false
},
{
"id": "stt_config",
"path": "stt/qwen3-asr/tokenizer/tokenizer_config.json",
"size": 12487,
"sha256": "4942d005604266809309cabc9f4e9cb89ce855d59b14681fdc0e1cc62ea26c4c",
"required": false
}
]
},
{
"id": "gemma_4_reasoning",
"name": "Gemma-4 Reasoning LLM",
"category": "llm",
"version": "1.0.0",
"files": [
{
"id": "llm_gemma_4_q4_k_m",
"path": "llm/gemma4/google_gemma-4-E2B-it-Q4_K_M.gguf",
"size": 3462678272,
"sha256": "b5310340b3a23d31655d7119d100d5df1b2d8ee17b3ca8b0a23ad7e9eb5fa705",
"required": false
}
]
},
{
"id": "llama_3_2_reasoning_q4",
"name": "Llama-3.2 Reasoning LLM (Q4)",
"category": "llm",
"version": "1.0.0",
"files": [
{
"id": "llm_llama_3_2_1b_instruct_q4_k_m",
"path": "llm/llama/Llama-3.2-1B-Instruct-Q4_K_M.gguf",
"size": 807694464,
"sha256": "6f85a640a97cf2bf5b8e764087b1e83da0fdb51d7c9fab7d0fece9385611df83",
"required": false
}
]
},
{
"id": "llama_3_2_reasoning",
"name": "Llama-3.2 Reasoning LLM (Q6)",
"category": "llm",
"version": "1.0.0",
"files": [
{
"id": "llm_llama_3_2_1b_instruct_q6_k",
"path": "llm/llama/Llama-3.2-1B-Instruct-Q6_K.gguf",
"size": 1021800576,
"sha256": "0f4c510daf16e0d1b3bc94931fd9296c28936bebdda2593687d4eb70c5b70628",
"required": false
}
]
},
{
"id": "gemma_4_uncensored",
"name": "Gemma-4 Uncensored LLM",
"category": "llm",
"version": "1.0.0",
"files": [
{
"id": "llm_gemma_4_e2b_uncensored_aggressive_q2_k_p",
"path": "llm/gemma4/Gemma-4-E2B-Uncensored-HauhauCS-Aggressive-Q2_K_P.gguf",
"size": 3009448896,
"sha256": "c9213a33b16d513482790bb7092243f783a450e35f7deca584a41e0470afdb97",
"required": false
}
]
},
{
"id": "supertonic_tts",
"name": "Supertonic 3 TTS Engine",
"category": "tts",
"version": "3.0.0",
"files": [
{
"id": "tts_supertonic_duration_predictor",
"path": "tts/supertonic-3/duration_predictor.int8.onnx",
"size": 3700147,
"sha256": "c3eb91414d5ff8a7a239b7fe9e34e7e2bf8a8140d8375ffb14718b1c639325db",
"required": false
},
{
"id": "tts_supertonic_text_encoder",
"path": "tts/supertonic-3/text_encoder.int8.onnx",
"size": 36416150,
"sha256": "c7befd5ea8c3119769e8a6c1486c4edc6a3bc8365c67621c881bbb774b9902ff",
"required": false
},
{
"id": "tts_supertonic_vector_estimator",
"path": "tts/supertonic-3/vector_estimator.int8.onnx",
"size": 78400833,
"sha256": "20cd86fa5c6effedfda0e7cffe5b0569ca401c440a0c3a1d72bf39286c0db3fd",
"required": false
},
{
"id": "tts_supertonic_vocoder",
"path": "tts/supertonic-3/vocoder.int8.onnx",
"size": 25991073,
"sha256": "e923d60f53f95eb1ce235f1dc33ec56d9c057823c96fa6f8acf98f32b0da6152",
"required": false
},
{
"id": "tts_supertonic_config",
"path": "tts/supertonic-3/tts.json",
"size": 8253,
"sha256": "42078d3aef1cd43ab43021f3c54f47d2d75ceb4e75f627f118890128b06a0d09",
"required": false
},
{
"id": "tts_supertonic_indexer",
"path": "tts/supertonic-3/unicode_indexer.bin",
"size": 262144,
"sha256": "8402ca48e5189a8950138580b0fff64db6f072f24ac07cd54ba8b2fbb9883b30",
"required": false
},
{
"id": "tts_supertonic_voice_bin",
"path": "tts/supertonic-3/voice.bin",
"size": 517168,
"sha256": "67d5209b0ee8ce6c74105ffbe12fe6a7628aea3b4ba2fcb308a4a67938a93ce8",
"required": false
}
]
},
{
"id": "chatterbox_tts",
"name": "Chatterbox Multilingual TTS Engine",
"category": "tts",
"version": "1.0.0",
"files": [
{
"id": "tts_chatterbox_t3",
"path": "tts/chatterbox/chatterbox-t3-mtl-q4_0.gguf",
"size": 344985408,
"sha256": "a7c8cbb267a836697a39757ada25a8ab095712b74961af2b86012dbd296a3a7b",
"required": false
},
{
"id": "tts_chatterbox_s3gen",
"path": "tts/chatterbox/chatterbox-s3gen-mtl-f16.gguf",
"size": 1056431360,
"sha256": "b25fe64c5b5287952c82684f6cadb12698257dfe8ed3d9e578801ca970b59664",
"required": false
}
]
}
]
}