PyThaiTTS v1.0.0 Released!

.github/workflows/test.yml

@@ -19,7 +19,7 @@ jobs:
       fail-fast: false
       matrix:
         os: [ubuntu-latest]
-        python-version: ['3.9', '3.10', '3.11']
+        python-version: ['3.10', '3.11']
 
     steps:
     - uses: actions/checkout@v4

README.md

@@ -38,6 +38,16 @@ from pythaitts import TTS
 tts = TTS(pretrained="fastthaig2p")
 file = tts.tts("สวัสดีครับ", speaker_idx="thai_som", filename="output.wav")
 
+# Use MakHamTTS Paradee (standalone, single-voice 8MB quantized INT8 ONNX model, offline without download)
+# MakHamTTS Paradee Sample Rate is 24000 Hz
+tts = TTS(pretrained="makham_paradee")
+file = tts.tts("สวัสดีค่ะ", filename="output.wav")
+
+# Use MakHamTTS (Kokoro-82M Thai base model, voices: newvoice_female, newvoice_male)
+# MakHamTTS Sample Rate is 24000 Hz
+tts = TTS(pretrained="makham")
+file = tts.tts("สวัสดีค่ะ", speaker_idx="newvoice_female", filename="output.wav")
+
 # Use Lunarlist ONNX
 # Sample Rate is 22050 Hz
 tts = TTS(pretrained="lunarlist_onnx")
@@ -142,6 +152,49 @@ print(eng("project"))                           # Output: /proː˧.t͡ɕek̚˨˩
 ```
 
 
+### Custom Word Pronunciation Dictionary
+
+PyThaiTTS supports custom word dictionaries to define custom Thai pronunciation (as Thai text reading or IPA phonemes) for specific words, acronyms, or names.
+
+Dictionaries can be passed as Python dicts, JSON files, or delimited text files (TSV, CSV, or colon-separated):
+
+```python
+from pythaitts import TTS
+
+# 1. Provide custom Thai pronunciation (hyphenated or plain text)
+custom_dict = {
+    "เพชรบุรี": "เพ็ด-ชะ-บุ-รี",
+    "สถิติ": "สะ-ถิ-ติ",
+    "ChatGPT": "แชตจีพีที",
+}
+
+tts = TTS(custom_dict=custom_dict)
+tts.tts("ยินดีต้อนรับสู่เพชรบุรี", filename="custom.wav")
+
+# 2. Or pass per-call or with IPA phonemes directly
+tts.tts(
+    "ผมไปเพชรบุรี",
+    custom_dict={"เพชรบุรี": "/pʰet̚˨˩.t͡ɕʰa˦˥.bu˨˩.riː˧/"},
+    filename="ipa.wav",
+)
+
+# 3. Add or update custom words dynamically
+tts.add_custom_dict({"ก.พ.": "กอ-พอ"})
+
+# 4. Load from a JSON or TSV file
+tts.set_custom_dict("my_words.json")
+```
+
+You can also use custom dictionaries with G2P directly:
+
+```python
+from pythaitts.pretrained.fastthaig2p import G2P
+
+g2p = G2P(custom_dict={"เพชรบุรี": "เพ็ด-ชะ-บุ-รี"})
+print(g2p.convert("ผมไปเพชรบุรี"))
+```
+
+
 ### Text Preprocessing
 
 PyThaiTTS includes automatic text preprocessing to improve TTS quality:

demo.py

@@ -41,6 +41,13 @@ def main():
         print(f"✓ Waveform generated successfully!")
         print(f"Waveform shape: {waveform.shape}")
         print()
+
+        # Demonstrate custom word pronunciation dictionary
+        print("Demonstrating custom word pronunciation dictionary...")
+        custom_dict = {"พายไทยทีทีเอส": "พาย-ไทย-ที-ที-เอส"}
+        waveform_custom = tts.tts(text, custom_dict=custom_dict, return_type="waveform")
+        print(f"✓ Custom pronunciation waveform generated! Shape: {waveform_custom.shape}")
+        print()
 
         print("=" * 60)
         print("Demo completed successfully!")

demo_realtime.py

@@ -23,7 +23,7 @@ def main():
     # 1. Initialize TTS model
     print("Initializing FastThaiG2P TTS model...")
     t_start = time.time()
-    tts = TTS(pretrained="fastthaig2p")
+    tts = TTS(pretrained="makham_paradee")
     print(f"✓ Model loaded in {time.time() - t_start:.2f}s")
     print()
 

docs/index.rst

@@ -40,6 +40,16 @@ PyThaiTTS provides English-to-Thai-IPA Grapheme-to-Phoneme (G2P) conversion for
 
 .. autofunction:: en_ipa_to_thai_ipa
 
+MakHamTTS Models
+----------------
+MakHamTTS models powered by Kokoro-82M Thai and Paradee 1.1 distillation.
+
+.. autoclass:: MakHamTTS
+   :members:
+
+.. autoclass:: MakHamTTSParadee
+   :members:
+
 FastThaiG2P Components
 ----------------------
 

example_realtime.py

@@ -14,7 +14,7 @@ def main():
     print("-" * 50)
 
     # Initialize FastThaiG2P TTS
-    tts = TTS(pretrained="fastthaig2p")
+    tts = TTS(pretrained="makham_paradee")
 
     # 1. Stream speech from text string chunk-by-chunk
     text = "สวัสดีครับ ยินดีต้อนรับสู่ระบบสังเคราะห์เสียงภาษาไทยแบบเรียลไทม์"