Model reference · open weights
MeloTTS-Korean is an open-weight audio or speech model from myshell-ai. MeloTTS-Korean (BF16) weighs 208 MB; the smallest configuration that runs it is RTX 3060 12 GB.
Summary of the myshell-ai/MeloTTS-Korean model card, 2026-10-01
What it is
| Released by | myshell-ai |
|---|---|
| Released | 2024-02-29 |
| VRAM | 208 MB for the weights |
What it runs on
| Card | One stream | Memory |
|---|---|---|
| RTX 3060 12 GB | fits | 11.6 GB |
| RTX 4060 Ti 16 GB | fits | 15.4 GB |
| RTX 3090 24 GB | fits | 23.4 GB |
| RTX 4090 24 GB | fits | 23.4 GB |
| RTX 5090 32 GB | fits | 31.0 GB |
| L40S 48 GB | fits | 44.0 GB |
| A100 80 GB | fits | 78.2 GB |
| H100 80 GB | fits | 78.1 GB |
| RTX PRO 6000 Blackwell 96 GB | fits | 93.8 GB |
| DGX Spark (GB10) 128 GB unified | fits | 107 GB |
| H200 141 GB | fits | 138 GB |
| B200 180 GB | fits | 176 GB |
From the model card
MeloTTS is a high-quality multi-lingual text-to-speech library by MyShell.ai. Supported languages include:
| Model card | Example |
|---|---|
| English (American) | Link |
| English (British) | Link |
| English (Indian) | Link |
| English (Australian) | Link |
| English (Default) | Link |
| Spanish | Link |
| French | Link |
| Chinese (mix EN) | Link |
| Japanese | Link |
| Korean | Link |
Some other features include:
mixed Chinese and English.CPU real-time inference.An unofficial live demo is hosted on Hugging Face Spaces.
There are hundreds of TTS models on MyShell, much more than MeloTTS. See examples here. More can be found at the widget center of MyShell.ai.
Follow the installation steps here before using the following snippet:
from melo.api import TTS
# Speed is adjustable
speed = 1.0
device = 'cpu' # or cuda:0
text = "안녕하세요! 오늘은 날씨가 정말 좋네요."
model = TTS(language='KR', device=device)
speaker_ids = model.hps.data.spk2id
output_path = 'kr.wav'
model.tts_to_file(text, speaker_ids['KR'], output_path, speed=speed)
Open Source AI Grant
We are actively sponsoring open-source AI projects. The sponsorship includes GPU resources, fundings and intellectual support (collaboration with top research labs). We welcome both reseach and engineering projects, as long as the open-source community needs them. Please contact Zengyi Qin if you are interested.
Contributing
If you find this work useful, please consider contributing to the GitHub repo.
This library is under MIT License, which means it is free for both commercial and non-commercial use.
This implementation is based on TTS, VITS, VITS2 and Bert-VITS2. We appreciate their awesome work.
Quoted from the model card on Hugging Face. The full card is behind the Hugging Face link above.
How it works