GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
SPRINGLab
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
SPRINGLab
Model Tree
Aratako/MioTTS-0.6B
Input Modalities
Output Modalities
Supported Functionality
For emotion and style control, place the tags at the end of the sentence.
For example: मुझे यह फिल्म बहुत पसंद आई! <happy> or I am not sure if I can do this. <confused>
Tags for Indian languages: <happy>, <sad>, <angry>, <disgust>, <fear>, <surprise>
Tags for English: <happy>, <sad>, <enunciated>, <confused>, <angry>, <whisper>
A word can be stressed by using asterisks(*) around it. For example: No! I could *never* do it!
Approach 1: With MioTTS-Inference (recommended)
Install vllm and set up MioTTS-Inference.
bash
vllm serve SPRINGLab/Indic-Mio --gpu-memory-utilization 0.5bash
cd MioTTS-Inferencepython run_server.pybash
python run_gradio.pyApproach 2: Directly with Transformers
bash
from transformers import AutoTokenizer, AutoModelForCausalLMfrom miocodec import MioCodecimport numpy as npimport torch model_name = "SPRINGLab/Indic-Mio"tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)model = AutoModelForCausalLM.from_pretrained( model_name, torch_dtype=torch.bfloat16, device_map="cuda") text = "नमस्ते, आप कैसे हैं?"messages = [{"role": "user", "content": text}]prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) inputs = tokenizer(prompt, return_tensors="pt").to(model.device)output = model.generate( **inputs, max_new_tokens=1024, temperature=0.9, top_p=0.9,) generated = output[0][inputs["input_ids"].shape[1]:]speech_offset = 151669audio_codes = [t.item() - speech_offset for t in generated if speech_offset <= t.item() < speech_offset + 12800] # Convert audio_codes by decoding with MioCodec# audio_codes -> numpy array -> MioCodec decode -> wav codec = MioCodec.from_pretrained("Aratako/MioCodec-25Hz-24kHz")codes_tensor = torch.tensor([audio_codes], dtype=torch.long).unsqueeze(0) # [1, 1, T]wav = codec.decode(codes_tensor) # -> [1, 1, num_samples] import soundfile as sfsf.write("output.wav", wav.squeeze().cpu().numpy(), 44100)This model was trained on a single NVIDIA A6000 ADA GPU in less than 6 hours.
For Indian languages, IndicTTS, Rasa and Syspin datasets were used. For American English, LibriTTS and Expresso, while for Indian English, SPICOR dataset was used.
This model is robust yet flexible. You can fine-tune it on your own dataset for better performance on specific languages, accents, speakers, styles or emotions. Just a few steps of LoRA fine-tuning can significantly improve the performance for your target task.
In case you use this model, please cite this huggingface repository as follows:
bibtex
@misc{indic-mio-tts, title={Indic-Mio TTS}, author={Advait Joglekar}, year={2026}, publisher = {Hugging Face}, howpublished={\url{https://huggingface.co/SPRINGLab/Indic-Mio}},}from transformers import AutoTokenizer, AutoModelForCausalLMfrom miocodec import MioCodecimport numpy as npimport torch model_name = "SPRINGLab/Indic-Mio"tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)model = AutoModelForCausalLM.from_pretrained( model_name, torch_dtype=torch.bfloat16, device_map="cuda") text = "नमस्ते, आप कैसे हैं?"messages = [{"role": "user", "content": text}]prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) inputs = tokenizer(prompt, return_tensors="pt").to(model.device)output = model.generate( **inputs, max_new_tokens=1024, temperature=0.9, top_p=0.9,) generated = output[0][inputs["input_ids"].shape[1]:]speech_offset = 151669audio_codes = [t.item() - speech_offset for t in generated if speech_offset <= t.item() < speech_offset + 12800] # Convert audio_codes by decoding with MioCodec# audio_codes -> numpy array -> MioCodec decode -> wav codec = MioCodec.from_pretrained("Aratako/MioCodec-25Hz-24kHz")codes_tensor = torch.tensor([audio_codes], dtype=torch.long).unsqueeze(0) # [1, 1, T]wav = codec.decode(codes_tensor) # -> [1, 1, num_samples] import soundfile as sfsf.write("output.wav", wav.squeeze().cpu().numpy(), 44100)@misc{indic-mio-tts, title={Indic-Mio TTS}, author={Advait Joglekar}, year={2026}, publisher = {Hugging Face}, howpublished={\url{https://huggingface.co/SPRINGLab/Indic-Mio}},}