• TTS - Text to Speech

• https://github.com/dwani-ai/tts-indic-server

  git clone https://github.com/dwani-ai/tts-indic-server
  cd tts-indic-server
  git checkout gh-200
  export HF_TOKEN='this-my-token'
  python -m venv  venv
  source venv/bin/activate
  pip install wheel packaging
  
  pip install -r requirements.txt
  
   pip uninstall torch torchaudio torchvision
  
  pip install torch==2.7.1 torchvision torchaudio --index-url https://download.pytorch.org/whl/cu128
  
  python src/gh200/main.py --host 0.0.0.0 --port 7864 --config config_two
  

---

TTS Indic Server

Overview

Text to Speech (TTS) for Indian languages using ai4bharat/IndicF5 model.

Table of Contents

• Live Server
• Usage
• How to Use the Service
  • High Latency Service
  • Low Latency Service
• Getting Started - Development
• For Development (Local)
• Downloading Indic TTS Model
• Running with FastAPI Server
• Evaluating Results
• Examples
  • Kannada
  • Hindi
• Specifying a Different Format
• Playing Back the Audio
• Describing the Voice
  • Describing the Voice with Specific Speaker - Suresh
  • Describing the Voice with Specific Speaker - Anu
• Building Docker Image
• Run the Docker Image
• Available Speakers
• Tips
• Description Examples
• Citations

Live Server

We have hosted a Text to Speech (TTS) service that can be used to verify the accuracy of Speech generation.

• Gradio Demo

Getting Started

For Development (Local)

• Prerequisites: Python 3.10, Ubuntu 22.04
• Steps:
• Create a virtual environment:

  python -m venv venv
  

• Activate the virtual environment:

  source venv/bin/activate
  

  On Windows, use:

  venv\Scripts\activate
  

• Install dependencies:

  pip install -r requirements.txt
  

Downloading Indic TTS Model

```bash download_model.sh huggingface_cli download ai4bharat/IndicF5

### Local Model Run
```python
from transformers import AutoModel
import numpy as np
import soundfile as sf

# Load INF5 from Hugging Face
repo_id = "ai4bharat/IndicF5"
model = AutoModel.from_pretrained(repo_id, trust_remote_code=True)


# Generate speech
audio = model(
    "ಬೆಂಗಳೂರು ಕರ್ನಾಟಕ ರಾಜ್ಯದ ರಾಜಧಾನಿ ಆಗಿದೆ, ಕರ್ನಾಟಕದಲ್ಲಿ ನಾವು ಕನ್ನಡ ಮಾತನಾಡುತ್ತೇವೆ",
    ref_audio_path="prompts/KAN_F_HAPPY_00001.wav",
    ref_text="ನಮ್‌ ಫ್ರಿಜ್ಜಲ್ಲಿ  ಕೂಲಿಂಗ್‌ ಸಮಸ್ಯೆ ಆಗಿ ನಾನ್‌ ಭಾಳ ದಿನದಿಂದ ಒದ್ದಾಡ್ತಿದ್ದೆ, ಆದ್ರೆ ಅದ್ನೀಗ ಮೆಕಾನಿಕ್ ಆಗಿರೋ ನಿಮ್‌ ಸಹಾಯ್ದಿಂದ ಬಗೆಹರಿಸ್ಕೋಬೋದು ಅಂತಾಗಿ ನಿರಾಳ ಆಯ್ತು ನಂಗೆ."
)


# Normalize and save output
if audio.dtype == np.int16:
    audio = audio.astype(np.float32) / 32768.0
sf.write("namaste.wav", np.array(audio, dtype=np.float32), samplerate=24000)

• Or Run the python code

  python tts_indic_f5.py
  

Contributing

We welcome contributions! Please read the CONTRIBUTING.md file for guidelines on how to contribute to this project.

Also you can join the discord group to collaborate

• Reference
  • ai4bharat/indic-parler-tts

Citations

```bibtex citation_1.bib @misc{lacombe-etal-2024-parler-tts, author = {Yoach Lacombe and Vaibhav Srivastav and Sanchit Gandhi}, title = {Parler-TTS}, year = {2024}, publisher = {GitHub}, journal = {GitHub repository}, howpublished = {\url{https://github.com/huggingface/parler-tts}} }

```bibtex citation_2.bib
@misc{lyth2024natural,
  title = {Natural language guidance of high-fidelity text-to-speech with synthetic annotations},
  author = {Dan Lyth and Simon King},
  year = {2024},
  eprint = {2402.01912},
  archivePrefix = {arXiv},
  primaryClass = {cs.SD}
}

@misc{AI4Bharat_IndicF5_2025,
  author       = {Praveen S V and Srija Anand and Soma Siddhartha and Mitesh M. Khapra},
  title        = {IndicF5: High-Quality Text-to-Speech for Indian Languages},
  year         = {2025},
  url          = {https://github.com/AI4Bharat/IndicF5},
}