biodatlab/ThonburianTTS

🔊 Model Checkpoints | 🤗 Gradio Demo | 📄 Thonburian TTS Paper

Thonburian TTS

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

Model Checkpoints

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

Quick Usage

Installation

Install dependencies:

pip install torch cached-path librosa transformers f5-tts
sudo apt install ffmpeg

Clone GitHub

git clone https://github.com/biodatlab/thonburian-tts.git
cd thonburian-tts

Loading Thai Script based Models

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)

Loading IPA based Models

from flowtts.inference import FlowTTSPipeline, ModelConfig, AudioConfig
import torch

# Configure F5-TTS model
model_config = ModelConfig(
    model_type="F5",
    checkpoint="hf://biodatlab/ThonburianTTS/megaIPA/model_last_prune.safetensors",
    vocab_file="hf://biodatlab/ThonburianTTS/megaIPA/mega_vocab_ipa.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)

Example Outputs

🎵 Sample 1 – Single-speaker Thai Normal Text

🎵 Sample 2 – Single-Speaker Thai Code-mixed Text

🎵 Sample 3 – Multi-Speaker Conversational Speech

---

Developers

• Looloo Technology
• Biomedical and Data Lab, Mahidol University

Citation

If you use ThonburianTTS in your research, please cite:

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,

License

The models are released under the Creative Commons Attribution Non-Commercial ShareAlike 4.0 License (CC BY-NC-SA 4.0).

Acknowledgement

We would like to acknowledge NSTDA Supercomputer Center (ThaiSC) project #pv824003 for providing computing resources for this work.