12 Indian Languages: Hindi, English, Telugu, Tamil, Marathi, Bengali, Kannada, Malayalam, Gujarati, Punjabi, Odia, Assamese
Male/Female Voices: Support for both genders
Low VRAM: ~6-8GB memory usage (FP8)
OpenAI-Compatible: /v1/audio/speech endpoint

Supported Languages

Language	Code
Hindi	hi
English	en
Telugu	te
Tamil	ta
Marathi	mr
Bengali	bn
Kannada	kn
Malayalam	ml
Gujarati	gu
Punjabi	pa
Odia	or
Assamese	as

Voice Format

Voice IDs: {language_code}_{gender}

Examples: hi_male, ta_female, en_male, bn_female

Usage

python

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model = AutoModelForCausalLM.from_pretrained(
    "srikantp/svara-tts-v1-fp8",
    torch_dtype=torch.bfloat16,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("srikantp/svara-tts-v1-fp8")

Requirements

NVIDIA GPU with 8GB+ VRAM
CUDA drivers
transformers, torch

Inference Code

For inference code, server, and web UI, see: svara-tts-inference-fp8

License

Apache 2.0 - See LICENSE file.

Citation

bibtex

@misc{svara-tts-v1-fp8,
  title={Svara TTS v1 FP8},
  author={srikantp},
  year={2025},
  url={https://huggingface.co/srikantp/svara-tts-v1-fp8}
}