Update README.md

README.md

@@ -1,49 +1,104 @@
 ---
-library_name: mlx-audio
+license: apache-2.0
+language:
+  - ar
+  - da
+  - de
+  - el
+  - en
+  - es
+  - fi
+  - fr
+  - he
+  - hi
+  - it
+  - ja
+  - ko
+  - ms
+  - nl
+  - no
+  - pl
+  - pt
+  - ru
+  - sv
+  - sw
+  - tr
+  - zh
 base_model:
 - ResembleAI/chatterbox
+pipeline_tag: text-to-speech
+library_name: mlx-audio
 tags:
+- text-to-speech
+- speech
+- speech generation
+- voice cloning
 - mlx
-pipeline_tag: text-to-speech
+- tts
 ---
 
-# litmudoc/Chatterbox-Multilingual-MLX-v2-fp16
-
-This model was converted to MLX format from [ResembleAI/chatterbox](https://huggingface.co/ResembleAI/chatterbox) using [mlx-audio](https://github.com/Blaizzy/mlx-audio) version **0.2.10**.
+# mlx-community/chatterbox-6bit
+This model was converted to MLX format from [`ResembleAI/chatterbox`](https://huggingface.co/ResembleAI/chatterbox) using mlx-audio version **0.2.7**.
+Refer to the [original model card](https://huggingface.co/ResembleAI/chatterbox) for more details on the model.
 
-**Note:** This model requires the S3Tokenizer weights from [mlx-community/S3TokenizerV2](https://huggingface.co/mlx-community/S3TokenizerV2), which will be downloaded automatically.
+## Use with mlx
 
-## Use with mlx-audio
+```bash
+pip install -U mlx-audio
+```
 
+### CLI Example:
 ```bash
-pip install -U git+https://github.com/litmudoc/mlx-audio.git@main mlx-audio
+python -m mlx_audio.tts.generate --model mlx-community/chatterbox-6bit --text "Hello, this is a test."
+```
+### Python Example:
+```python
+from mlx_audio.tts.utils import load_model
+from mlx_audio.tts.generate import generate_audio
+model = load_model("mlx-community/chatterbox-6bit")
+generate_audio(
+    model=model, text="Hello, this is a test.",
+    file_prefix="test_audio",
+)
 ```
 
-### Command line
+### Voice Cloning: 
+```python
+from mlx_audio.tts.generate import generate_audio
 
-```bash
-curl -L -o ko.wav https://huggingface.co/litmudoc/Chatterbox-Multilingual-MLX-v2-fp16/blob/main/ko.wav
-
-mlx_audio.tts.generate \
-  --model litmudoc/Chatterbox-Multilingual-MLX-v2-fp16 \
-  --text ", 지난달 우리는 유튜브 채널에서 이십억 조회수라는 새로운 이정표에 도달했습니다." \
-  --lang_code ko \
-  --ref_audio ko.wav \
-  --ref_text "우리는 정말로 허름한 호텔에 묵었지만, 그래도 행복했다." \
-  --verbose --play
+generate_audio(
+    text="Hello, this is a test of Chatterbox TTS.",
+    model="mlx-community/chatterbox-6bit",
+    ref_audio="path_to_file.wav",
+    ref_text="Text transcript", # Optional
+    file_prefix="vc_output",
+)
 ```
 
-### Python
+## Multilingual Quickstart
+
+Generate speech in 23 languages by specifying the `lang_code` parameter. The model automatically handles pronunciation, intonation, and language-specific phonemes.
 
 ```python
 from mlx_audio.tts.generate import generate_audio
 
 generate_audio(
-    text=", 지난달 우리는 유튜브 채널에서 이십억 조회수라는 새로운 이정표에 도달했습니다.",
-    model="litmudoc/Chatterbox-Multilingual-MLX-v2-fp16",
-    lang_code="ko",
-    ref_audio="ko.wav",
-    ref_text="우리는 정말로 허름한 호텔에 묵었지만, 그래도 행복했다.",
-    file_prefix="output",
+    text="Olá, tudo bem?",
+    model="mlx-community/chatterbox-6bit",
+    lang_code="pt",
+    file_prefix="multilingual_output",
 )
 ```
+
+### Supported Languages
+
+| Code | Language   | Code | Language   | Code | Language   |
+|------|------------|------|------------|------|------------|
+| `ar` | Arabic     | `he` | Hebrew     | `no` | Norwegian  |
+| `da` | Danish     | `hi` | Hindi      | `pl` | Polish     |
+| `de` | German     | `it` | Italian    | `pt` | Portuguese |
+| `el` | Greek      | `ja` | Japanese   | `ru` | Russian    |
+| `en` | English    | `ko` | Korean     | `sv` | Swedish    |
+| `es` | Spanish    | `ms` | Malay      | `sw` | Swahili    |
+| `fi` | Finnish    | `nl` | Dutch      | `tr` | Turkish    |
+| `fr` | French     | `zh` | Chinese    |      |            |