silma-tts 1.0.1

SILMA TTS: A Lightweight Open Bilingual Text to Speech Model

SILMA TTS: A Lightweight Open Bilingual Text to Speech Model

SILMA TTS v1 is a high-performance, 150M-parameter bilingual (Arabic/English) TTS model developed by SILMA AI. Built on the cutting-edge F5-TTS diffusion architecture, the model was pretrained from scratch using tens of thousands of hours of high-quality public and proprietary data. To give back to the community, SILMA TTS is released under a highly permissive license, making state-of-the-art speech synthesis accessible for both research and commercial use.

Features

1. High-Fidelity Audio: Superior speech synthesis with high-quality output
2. Lightweight 150M Parameter Model: works well in low-resource environments
3. Instant Voice Cloning
4. Ultra-Low Latency: Optimized for real-time applications with RTF around 0.19 (A40 GPU)
5. Bilingual Arabic & English Support: Native-level fluency across both languages
6. Advanced Arabic Diacritization: Full support for Tashkeel to ensure precise pronunciation and context
7. Text Normalization: utilizing NeMo Text Processing
8. Commercial-Friendly Licensing: Fully open-source under the Apache 2.0 License

Installation

Using pip

# make sure ffmpeg is installed
apt-get update && apt install ffmpeg -y

# create and activate the environment
python -m venv silma-tts-env
source silma-tts-env/bin/activate

# install silma-tts library
pip install silma_tts

From source

# make sure ffmpeg is installed
apt-get update && apt install ffmpeg -y

# create and activate the environment
python -m venv silma-tts-env
source silma-tts-env/bin/activate

# clone repo and install
git clone https://github.com/SILMA-AI/silma-tts.git
cd silma-tts
pip install -e .

Usage & Inference

Using gradio app

# Run the following command
silma-tts-app

Then open the following browser link http://127.0.0.1:7860/

Inference using python

import time
from silma_tts.api import SilmaTTS

silma_tts = SilmaTTS()

## the voice/style you want to clone
reference_audio_file = "/root/silma-tts/src/silma_tts/infer/ref_audio_samples/ar.ref.24k.wav"
## the transcription of the reference_audio_file
reference_audio_text = "ويدقق النظر في القرآن الكريم وسائر الكتب السماوية ويتبع مسالك الرسل العظام عليهم الصلاة والسلام."

time_start = time.time()

wav, sr, spec = silma_tts.infer(
    ref_file=reference_audio_file,
    ref_text=reference_audio_text, # can also be left None - will be transcribed on the fly
    gen_text="""
    أنا نموذج جديد من سلمى لتحويل النص إلى كلام، يمكنني التحدث باللغة العربية مع أو بدون علامات التشكيل.
    I am the new SILMA model for converting text to speech, I can speak Arabic with or without diacritics.
    """.strip(),
    file_wave=str("generated_audio.wav"),
    seed=None,
    speed=1
)

time_end = time.time()
print(f"Time elapsed:{(time_end-time_start):.2f} seconds")

## Note 1: generated audio file (generated_audio.wav) will be saved in the current directory
## Note 2: You can also use the "wav" variable (raw waveform) to play the audio to return it via API

You can run the example above directly using the following command:

python src/silma_tts/infer/example.py

Training

Our model is 100% compatible with F5-TTS v1.1.7. This means you can make use of all the great resources, tools and community experince in the F5-TTS project.

Steps

## clone F5-TTS v1.1.7
git clone --depth 1  --branch v1.1.7 https://github.com/SWivid/F5-TTS.git
cd F5-TTS
pip install -e .

## download silma-tts model weights, vocab.txt and config.yaml
hf download silma-ai/silma-tts . --local-dir /root/silma-tts

## open F5-TTS UI training pipeline 
f5-tts_infer-gradio --port 7860 --host 0.0.0.0

## follow the F5-TTS training guide below
## https://github.com/SWivid/F5-TTS/tree/main/src/f5_tts/train

Summary: you need to use the F5-TTS v1.1.7 training code, but use our config file, vocab, and our pretrained weights

Acknowledgements

This repo builds directly upon the excellent foundation laid by the F5-TTS project. The core architecture and the majority of the code is derived from their work. Our work introduces new pretrained weights and significant optimizations to the inference code.

Support

Unfortunately we don't have capacity to actively support this repo. We also believe it is best to consolidate resources and knowledge in a single location. This is why we encourage you to visit the official F5-TTS repository, which is highly active and supported by a fantastic community.

• Please check if your question is already answered in the F5-TTS Issues or open a new issue
• We monitor the F5-TTS Issues and will engage there if needed
• If you have a question that you think only us can answer, then please open a community discussion on our HuggingFace repo

Citation

@article{silma-tts-v1,
      title={SILMA TTS: A Lightweight Open Bilingual Text to Speech Model}, 
      author={SILMA AI},
      year={2026},
}

License

1. Code: MIT License
2. Model Weights: Apache-2.0 License