Text-to-Speech
Safetensors
Chatterbox
MLX
mlx-audio
multilingual
voice-cloning
8-bit precision
affine
omlx
Instructions to use groxaxo/chatterbox-multilingual-MLX-Q8-G64 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use groxaxo/chatterbox-multilingual-MLX-Q8-G64 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download groxaxo/chatterbox-multilingual-MLX-Q8-G64 --local-dir chatterbox-multilingual-MLX-Q8-G64
- Chatterbox
How to use groxaxo/chatterbox-multilingual-MLX-Q8-G64 with Chatterbox:
# pip install chatterbox-tts import torchaudio as ta from chatterbox.tts import ChatterboxTTS model = ChatterboxTTS.from_pretrained(device="cuda") text = "Ezreal and Jinx teamed up with Ahri, Yasuo, and Teemo to take down the enemy's Nexus in an epic late-game pentakill." wav = model.generate(text) ta.save("test-1.wav", wav, model.sr) # If you want to synthesize with a different voice, specify the audio prompt AUDIO_PROMPT_PATH="YOUR_FILE.wav" wav = model.generate(text, audio_prompt_path=AUDIO_PROMPT_PATH) ta.save("test-2.wav", wav, model.sr) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
chatterbox-multilingual-MLX-Q8-G64 / experiments /omlx-q6-q8-2026-10-09 /docs /performance /weight-validation.json
Download experiments/omlx-q6-q8-2026-10-09/docs/performance/weight-validation.json from groxaxo/chatterbox-multilingual-MLX-Q8-G64: direct link, hf CLI and curl.
- Browser
- Download file 979 Bytes
-
https://huggingface.co/groxaxo/chatterbox-multilingual-MLX-Q8-G64/resolve/main/experiments/omlx-q6-q8-2026-10-09/docs/performance/weight-validation.json
- Command line
-
hf download hf://groxaxo/chatterbox-multilingual-MLX-Q8-G64/experiments/omlx-q6-q8-2026-10-09/docs/performance/weight-validation.json
-
curl -L -o weight-validation.json https://huggingface.co/groxaxo/chatterbox-multilingual-MLX-Q8-G64/resolve/main/experiments/omlx-q6-q8-2026-10-09/docs/performance/weight-validation.json
979 Bytes
| { | |
| "source_repo": "mlx-community/chatterbox-multilingual-v3", | |
| "source_revision": "03565773edd72e949572557597af8063bb49a18a", | |
| "source_sha256": "e702f2c441e040bd360e59a86c85d462539759d665e41cfd1938adadd74187a3", | |
| "q6_sha256": "392f8758a072a70a44ec5c70351a9502877880a196377c74d90cf006a8f06c8c", | |
| "source_bytes": 2711113780, | |
| "q6_bytes": 718359417, | |
| "quantized_main_matrices": 651, | |
| "bitwise_unchanged_tensor_count": 1836, | |
| "bitwise_unchanged_tensor_bytes": 159837884, | |
| "component_counts": { | |
| "ve": 1, | |
| "s3gen": 428, | |
| "t3": 222 | |
| }, | |
| "external_s3_repo": "mlx-community/S3TokenizerV2", | |
| "external_s3_revision": "e0c9886f0e1c35ae85b1f27277416fb19fc72bec", | |
| "external_s3_sha256": "928726bc1f206a613d36b8f49e297eae9c5593a21bf9b92ddfe2c23f85eb92cc", | |
| "external_s3_bytes": 494868984, | |
| "quantizer": "oMLX _quantize_chunked (native MLX affine path), revision 70f44cfd", | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine", | |
| "external_s3_q6_runtime_matrices": 37 | |
| } | |