Text-to-Speech
MLX
Safetensors
Chinese
English
tts
speech
voice-conditioned
multi-speaker
long-form
diffusion
apple-silicon
quantized
8bit
Instructions to use appautomaton/vibevoice-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use appautomaton/vibevoice-mlx with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download appautomaton/vibevoice-mlx --local-dir vibevoice-mlx
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download mlx-int8/preprocessor_config.json from appautomaton/vibevoice-mlx: direct link, hf CLI and curl.
- Browser
- Download file 349 Bytes
-
https://huggingface.co/appautomaton/vibevoice-mlx/resolve/main/mlx-int8/preprocessor_config.json
- Command line
-
hf download hf://appautomaton/vibevoice-mlx/mlx-int8/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/appautomaton/vibevoice-mlx/resolve/main/mlx-int8/preprocessor_config.json
349 Bytes
| { | |
| "processor_class": "VibeVoiceProcessor", | |
| "speech_tok_compress_ratio": 3200, | |
| "db_normalize": true, | |
| "audio_processor": { | |
| "feature_extractor_type": "VibeVoiceTokenizerProcessor", | |
| "sampling_rate": 24000, | |
| "normalize_audio": true, | |
| "target_dB_FS": -25, | |
| "eps": 1e-06 | |
| }, | |
| "language_model_pretrained_name": "Qwen/Qwen2.5-7B" | |
| } |