indic parler tts

Providerai4bharat
Categorytext-to-speech
Licenseapache-2.0
Downloads62
Stars0

Overview

Indic Parler TTS is an open-source text-to-speech framework specifically engineered for the diverse linguistic landscape of the Indian subcontinent. Unlike generic global TTS models, this model is optimized for the phonetic nuances and tonal variations of Indic languages, reducing the robotic cadence often found in multilingual systems. For developers, it offers a flexible integration path under the Apache-2.0 license, making it suitable for both commercial and research-driven applications. It is particularly effective for building localized voice assistants, accessibility tools, and automated content narration where regional language accuracy is critical. By prioritizing high-fidelity synthesis for underserved languages, it fills a significant gap in the current TTS ecosystem, providing a performant alternative to proprietary APIs.

Highlights

  • Optimized for high-fidelity synthesis of Indic languages
  • Permissive Apache-2.0 license for commercial deployment
  • Reduces phonetic errors common in global TTS models
  • Ideal for localized voice assistants and accessibility apps
  • Efficient integration for regional language content automation

Usage

Install
# Install Hugging Face transformers
pip install transformers torch
SDK Usage
# Load model with transformers
from transformers import AutoModel, AutoTokenizer

model = AutoModel.from_pretrained("ai4bharat/indic-parler-tts")
tokenizer = AutoTokenizer.from_pretrained("ai4bharat/indic-parler-tts")

Hugging Face Download

We recommend downloading the model via the Hugging Face CLI or Hub SDK.

Guidance：Before downloading, install huggingface_hub with:

Guidance 
pip install -U huggingface_hub

CLI Download

Download the full repository

Download the full repository 
huggingface-cli download ai4bharat/indic-parler-tts

Download a single file to a local folder (e.g. config.json into ./dir)

Download a single file to a local folder (e.g. config.json into ./dir) 
huggingface-cli download ai4bharat/indic-parler-tts config.json --local-dir ./dir

See the official docs for more CLI options

SDK Download

SDK Download 
# 模型下载
from huggingface_hub import snapshot_download
model_dir = snapshot_download('ai4bharat/indic-parler-tts')

Git Download

Make sure git-lfs is installed first

Git Download 
git lfs install
git clone https://huggingface.co/ai4bharat/indic-parler-tts

To skip LFS large-file downloads, use:

Skip LFS 
GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/ai4bharat/indic-parler-tts

Model files are hosted on the Hugging Face Hub — download directly via HF CLI / SDK / Git, not through this site.

PyTorch / Transformers Usage

Install Transformers

Install Transformers 
pip install -U transformers torch

Load the model and run inference

Load the model and run inference 
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained('ai4bharat/indic-parler-tts')
tokenizer = AutoTokenizer.from_pretrained('ai4bharat/indic-parler-tts')

Model Download

We recommend downloading the model via the ModelScope CLI or SDK.

Guidance：Before downloading, install ModelScope with:

Guidance 
pip install modelscope

CLI Download

Download the full repository

Download the full repository 
modelscope download --model ai4bharat/indic-parler-tts

Download a single file to a local folder (e.g. README.md into ./dir)

Download a single file to a local folder (e.g. README.md into ./dir) 
modelscope download --model ai4bharat/indic-parler-tts README.md --local_dir ./dir

See the docs for more CLI options

SDK Download

SDK Download 
# 模型下载
from modelscope import snapshot_download
model_dir = snapshot_download('ai4bharat/indic-parler-tts')

Git Download

Make sure git-lfs is installed first

Git Download 
git lfs install
git clone https://www.modelscope.cn/ai4bharat/indic-parler-tts.git

To skip LFS large-file downloads, use:

Skip LFS 
GIT_LFS_SKIP_SMUDGE=1 git clone https://www.modelscope.cn/ai4bharat/indic-parler-tts.git

ModelScope 模型页直接下载模型文件；无需将模型文件放在本站服务器。

Notebook Quickstart

Install the ModelScope library

Install the ModelScope library 
pip install "modelscope[audio,cv,nlp,multi-modal,science]" -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html

Load the model and run inference

Load the model and run inference 
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks

p = pipeline('text-generation', 'ai4bharat/indic-parler-tts')
View official source
Join our Telegram