🔊 Model Checkpoints | 🤗 Gradio Demo | 📄 ThonburianTTS Paper | Colab Notebook | GitHub
Thonburian TTS is a Thai Text-to-Speech (TTS) engine built on top of the F5-TTS.
It generates natural and expressive Thai speech by leveraging Flow-Matching diffusion techniques and can mimic reference voices from short audio samples. The system supports:
- Thai language generation (
language="th") - Reference-based voice cloning using short audio clips
- High-quality synthesis with controllable speed and silence trimming
This workflow enables:
- High-quality Thai speech generation from text
- Voice cloning with style and tone preservation
- ASR-TTS integration for interactive voice applications
Below is a minimal example for generating Thai speech with voice cloning using a reference sample.
from flowtts.inference import FlowTTSPipeline, ModelConfig, AudioConfig
import torch
# Configure F5-TTS model
model_config = ModelConfig(
language="th",
model_type="F5",
checkpoint="hf://biodatlab/ThonburianTTS/megaF5/mega_f5_last.safetensors",
vocab_file="hf://biodatlab/ThonburianTTS/megaF5/mega_vocab.txt",
vocoder="vocos",
device="cuda" if torch.cuda.is_available() else "cpu"
)
# Basic audio settings
audio_config = AudioConfig(
silence_threshold=-45,
cfg_strength=2.5,
speed=1.0
)
pipeline = FlowTTSPipeline(model_config, audio_config)
# Input text and reference voice
text = "ยินดีที่ได้รู้จักคุณวันนี้อากาศดีมาก"
ref_voice = "ref_samples/ref_sample.wav"
ref_text = "ยินดีที่ได้รู้จัก" # Manual transcript of the reference clip
# Generate speech
output_path = pipeline(
text=text,
ref_voice=ref_voice,
ref_text=ref_text,
output_file="f5_output.wav"
)
print(f"Generated F5 audio saved to: {output_path}")Install dependencies:
pip install torch cached-path librosa transformers f5-tts
sudo apt install ffmpeg| Model Component | Description | URL |
|---|---|---|
| F5-TTS Thai | Flow Matching-based Thai TTS models | Link |
| F5-TTS IPA | Flow Matching-based Thai-IPA TTS models | Link |
 🎵 Sample 1 – Single-speaker Thai Normal Text |
 🎵 Sample 2 – Single-Speaker Thai Code-mixed Text |
 🎵 Sample 3 – Multi-Speaker Conversational Speech |
If you use ThonburianTTS in your research, please cite:
@INPROCEEDINGS{11320472,
author={Aung, Thura and Sriwirote, Panyut and Thavornmongkol, Thanachot and Pipatsrisawat, Knot and Achakulvisut, Titipat and Aung, Zaw Htet},
booktitle={2025 20th International Joint Symposium on Artificial Intelligence and Natural Language Processing (iSAI-NLP)},
title={ThonburianTTS: Enhancing Neural Flow Matching Models for Authentic Thai Text-to-Speech},
year={2025},
volume={},
number={},
pages={1-6},
keywords={Adaptation models;Codes;Accuracy;Error analysis;Phonetics;Robustness;Natural language processing;Text to speech;Noise measurement;Research and development;Thai text-to-speech;Flow matching;F5-TTS},
doi={10.1109/iSAI-NLP66160.2025.11320472}}
Thura Aung, Panyut Sriwirote, Thanachot Thavornmongkol, Knot Pipatsrisawat, Titipat Achakulvisut, Zaw Htet Aung, "ThonburianTTS: Enhancing Neural Flow Matching Models for Authentic Thai Text-to-Speech", 2025 20th International Joint Symposium on Artificial Intelligence and Natural Language Processing (iSAI-NLP), Phuket, Thailand, 2025, pp. 1-6, doi: 10.1109/iSAI-NLP66160.2025.11320472.
Our codes are released under the MIT License. The models are released under the Creative Commons Attribution Non-Commercial ShareAlike 4.0 License (CC BY-NC-SA 4.0).