[Feature] TTS: Support [pause:xx] Tags, Auto-Editor Cleanup, and Dependency Upgrade

README.md

@@ -26,6 +26,8 @@ If you like the model but need to scale or tune it for higher accuracy, check ou
 - Watermarked outputs
 - Easy voice conversion script
 - [Outperforms ElevenLabs](https://podonos.com/resembleai/chatterbox)
+- Smart artifact cleaning with pause protection
+- Support for custom pause tags `[pause:xx]`
 
 # Supported Languages 
 Arabic (ar) • Danish (da) • German (de) • Greek (el) • English (en) • Spanish (es) • Finnish (fi) • French (fr) • Hebrew (he) • Hindi (hi) • Italian (it) • Japanese (ja) • Korean (ko) • Malay (ms) • Dutch (nl) • Norwegian (no) • Polish (pl) • Portuguese (pt) • Russian (ru) • Swedish (sv) • Swahili (sw) • Turkish (tr) • Chinese (zh)
@@ -84,6 +86,15 @@ ta.save("test-chinese.wav", wav_chinese, model.sr)
 AUDIO_PROMPT_PATH = "YOUR_FILE.wav"
 wav = model.generate(text, audio_prompt_path=AUDIO_PROMPT_PATH)
 ta.save("test-2.wav", wav, model.sr)
+
+# Using artifact cleaning feature
+wav = model.generate(
+    text="Hello[pause:0.5s]world!",  # Support [pause:xx] tag for adding pauses
+    use_auto_editor=True,            # Enable artifact cleaning
+    ae_threshold=0.06,               # Volume threshold (0-1)
+    ae_margin=0.2                    # Boundary protection time (seconds)
+)
+ta.save("test-3.wav", wav, model.sr)
 ```
 See `example_tts.py` and `example_vc.py` for more examples.
 

pyproject.toml

@@ -10,6 +10,7 @@ authors = [
 ]
 dependencies = [
     "numpy>=1.24.0,<1.26.0",
+    "resampy==0.4.3",
     "librosa==0.11.0",
     "s3tokenizer",
     "torch==2.6.0",
@@ -23,7 +24,7 @@ dependencies = [
     "pykakasi==2.3.0",
     "gradio==5.44.1",
     "russian-text-stresser @ git+https://github.com/Vuizur/add-stress-to-epub",
-
+    "auto-editor>=27.0.0"
 ]
 
 [project.urls]
@@ -36,3 +37,10 @@ build-backend = "setuptools.build_meta"
 
 [tool.setuptools.packages.find]
 where = ["src"]
+
+[dependency-groups]
+dev = [
+    "gradio>=4.44.1",
+    "resemble-perth>=1.0.1",
+    "setuptools>=80.9.0",
+]

src/chatterbox/__init__.py

@@ -8,4 +8,5 @@
 
 from .tts import ChatterboxTTS
 from .vc import ChatterboxVC
-from .mtl_tts import ChatterboxMultilingualTTS, SUPPORTED_LANGUAGES
+from .mtl_tts import ChatterboxMultilingualTTS, SUPPORTED_LANGUAGES
+from .text_utils import split_text_into_segments, split_by_word_boundary, merge_short_sentences