Text-to-Speech
Transformers
Safetensors
higgs_multimodal_qwen3
text-generation
speech-generation
voice-agent
expressive-speech
controllable-tts
multilingual-tts
Instructions to use bosonai/higgs-audio-v3-tts-4b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use bosonai/higgs-audio-v3-tts-4b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="bosonai/higgs-audio-v3-tts-4b")# Load model directly from transformers import AutoModelForSeq2SeqLM model = AutoModelForSeq2SeqLM.from_pretrained("bosonai/higgs-audio-v3-tts-4b", dtype="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "_hidden_size": 2560, | |
| "_vocab_size": 151936, | |
| "architectures": [ | |
| "HiggsMultimodalQwen3ForConditionalGeneration" | |
| ], | |
| "audio_encoder_config": { | |
| "_name_or_path": "", | |
| "architectures": null, | |
| "chunk_size_feed_forward": 0, | |
| "dtype": null, | |
| "encoder_type": "discrete", | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "is_encoder_decoder": false, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "max_chunk_size": 50, | |
| "mel_per_sample": 8, | |
| "model_type": "higgs_audio_encoder", | |
| "num_codebooks": 8, | |
| "out_dim": 2560, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "problem_type": null, | |
| "qwen3_aut_config": null, | |
| "return_dict": true, | |
| "tie_word_embeddings": true, | |
| "use_delay_pattern": true, | |
| "vocab_size": 1026, | |
| "whisper_config": null | |
| }, | |
| "audio_token_id": -100, | |
| "ignore_index": -100, | |
| "model_type": "higgs_multimodal_qwen3", | |
| "text_config": { | |
| "_name_or_path": "/ceph/models/Qwen3-4B-Base", | |
| "architectures": [ | |
| "Qwen3ForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 151643, | |
| "dtype": "bfloat16", | |
| "eos_token_id": 151643, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 2560, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 9728, | |
| "layer_types": [ | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention" | |
| ], | |
| "max_position_embeddings": 32768, | |
| "max_window_layers": 36, | |
| "model_type": "qwen3", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 36, | |
| "num_key_value_heads": 8, | |
| "pad_token_id": null, | |
| "rms_norm_eps": 1e-06, | |
| "rope_parameters": { | |
| "rope_theta": 1000000, | |
| "rope_type": "default" | |
| }, | |
| "sliding_window": null, | |
| "tie_word_embeddings": true, | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "vocab_size": 151936 | |
| }, | |
| "transformers_version": "5.5.0" | |
| } | |