Model reference · open weights
MeloTTS-English is an open-weight audio or speech model from myshell-ai, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
MeloTTS MeloTTS is a high-quality multi-lingual text-to-speech library by MIT and MyShell.ai. Supported languages include: Some other features include: - The Chinese speaker supports mixed Chinese and English. - Fast enough for CPU real-time inference. Authors - Wenliang Zhao at Tsinghua University - Xumin Yu at Tsinghua University - Zengyi Qin (project lead) at MIT and MyShell Citation Usage Without Installation An unofficial live demo is hosted on Hugging Face Spaces. Use it on MyShell 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. Install and Use Locally Follow the installation steps here before using the following snippet: Join the Community 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. - Many thanks to @fakerybakery for adding the Web UI and CLI part. License This library is under MIT License, which means it is free for both commercial and non-commercial use. Acknowledgements This implementation is based on TTS, VITS, VITS2 and Bert-VITS2. We appreciate their awesome work.
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | myshell-ai |
|---|---|
| Type | Audio & music |
| Variants | 1 |
| Runs with | transformers |
| Released | 2024-02-29 |
| Popularity | 191k downloads / month |
| Likes | 315 |
| Licence | Open weights |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| MeloTTS-English | — | BF16 | — | — | Weights ↗ |
Using it via the API
Once AxForge deploys melotts-english for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (melotts-english below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/audio/transcriptions \ -H "Authorization: Bearer $AXFORGE_API_KEY" \ -F model="melotts-english" -F file=@audio.mp3
Details
Languages
Tags
Licence
Open weights under mit — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗