https://github.com/myshell-ai/openvoice
Instant voice cloning by MIT and MyShell. Audio foundation model.
Science Score: 46.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
○CITATION.cff file
-
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
○DOI references
-
✓Academic publication links
Links to: arxiv.org -
✓Committers with academic emails
1 of 14 committers (7.1%) from academic institutions -
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (15.1%) to scientific vocabulary
Keywords
Keywords from Contributors
Repository
Instant voice cloning by MIT and MyShell. Audio foundation model.
Basic Info
- Host: GitHub
- Owner: myshell-ai
- License: mit
- Language: Python
- Default Branch: main
- Homepage: https://research.myshell.ai/open-voice
- Size: 3.76 MB
Statistics
- Stars: 32,737
- Watchers: 235
- Forks: 3,418
- Open Issues: 262
- Releases: 0
Topics
Metadata Files
README.md
[Paper](https://arxiv.org/abs/2312.01479) |
[Website](https://research.myshell.ai/open-voice) Introduction
OpenVoice V1
As we detailed in our paper and website, the advantages of OpenVoice are three-fold:
1. Accurate Tone Color Cloning. OpenVoice can accurately clone the reference tone color and generate speech in multiple languages and accents.
2. Flexible Voice Style Control. OpenVoice enables granular control over voice styles, such as emotion and accent, as well as other style parameters including rhythm, pauses, and intonation.
3. Zero-shot Cross-lingual Voice Cloning. Neither of the language of the generated speech nor the language of the reference speech needs to be presented in the massive-speaker multi-lingual training dataset.
OpenVoice V2
In April 2024, we released OpenVoice V2, which includes all features in V1 and has:
1. Better Audio Quality. OpenVoice V2 adopts a different training strategy that delivers better audio quality.
2. Native Multi-lingual Support. English, Spanish, French, Chinese, Japanese and Korean are natively supported in OpenVoice V2.
3. Free Commercial Use. Starting from April 2024, both V2 and V1 are released under MIT License. Free for commercial use.
OpenVoice has been powering the instant voice cloning capability of myshell.ai since May 2023. Until Nov 2023, the voice cloning model has been used tens of millions of times by users worldwide, and witnessed the explosive user growth on the platform.
Main Contributors
- Zengyi Qin at MIT
- Wenliang Zhao at Tsinghua University
- Xumin Yu at Tsinghua University
- Ethan Sun at MyShell
How to Use
Please see usage for detailed instructions.
Common Issues
Please see QA for common questions and answers. We will regularly update the question and answer list.
Citation
@article{qin2023openvoice,
title={OpenVoice: Versatile Instant Voice Cloning},
author={Qin, Zengyi and Zhao, Wenliang and Yu, Xumin and Sun, Xin},
journal={arXiv preprint arXiv:2312.01479},
year={2023}
}
License
OpenVoice V1 and V2 are MIT Licensed. Free for both commercial and research use.
Acknowledgements
This implementation is based on several excellent projects, TTS, VITS, and VITS2. Thanks for their awesome work!
Owner
- Name: myshell-ai
- Login: myshell-ai
- Kind: organization
- Repositories: 1
- Profile: https://github.com/myshell-ai
Committers
Last synced: 10 months ago
Top Committers
| Name | Commits | |
|---|---|---|
| Zengyi Qin | q****s@g****m | 65 |
| wl-zhao | z****0@m****n | 14 |
| Xumin Yu | 1****6@q****m | 6 |
| Alienpups | 4****s | 5 |
| Shreeram | s****v@l****m | 4 |
| pqdong | 4****g | 2 |
| Xin Sun | i****o@x****o | 2 |
| remorses | b****e@g****m | 1 |
| Sulthan Abiyyu Hakim | 6****u | 1 |
| Ikko Eltociear Ashimine | e****r@g****m | 1 |
| Frank Du | f****0@g****m | 1 |
| Felipe Moreira Ferreira | f****a@l****m | 1 |
| Drishya Karki | 9****i | 1 |
| jorisSchaller | j****r@p****m | 1 |
Committer Domains (Top 20 + Academic)
Issues and Pull Requests
Last synced: 7 months ago
All Time
- Total issues: 96
- Total pull requests: 17
- Average time to close issues: 22 days
- Average time to close pull requests: about 4 hours
- Total issue authors: 88
- Total pull request authors: 10
- Average comments per issue: 1.29
- Average comments per pull request: 0.0
- Merged pull requests: 2
- Bot issues: 0
- Bot pull requests: 0
Past Year
- Issues: 81
- Pull requests: 17
- Average time to close issues: 1 day
- Average time to close pull requests: about 4 hours
- Issue authors: 76
- Pull request authors: 10
- Average comments per issue: 1.1
- Average comments per pull request: 0.0
- Merged pull requests: 2
- Bot issues: 0
- Bot pull requests: 0
Top Authors
Issue Authors
- Salasarcyber (10)
- zhjygit (4)
- ban1989ban (2)
- dilerbatu (2)
- tushar-31093 (2)
- antonsanchez (2)
- GayathriGanapathy (2)
- dhvms99 (2)
- ladibahmed (2)
- hrishi-04 (2)
- quantum304 (2)
- nn1k4 (2)
- fury88 (2)
- yukiarimo (2)
- furqan4545 (2)
Pull Request Authors
- pq-dong (4)
- eltociear (3)
- Zengyi-Qin (3)
- PiyushDuggal-source (2)
- joeyparrish (2)
- derpoliuk (2)
- skyleraiguy (2)
- HERIUN (2)
- sethclim (2)
- Grvkk (2)
- iamshreeram (2)
- teruzhang (1)
- StevenJSCF (1)
- DontCallMyPhoneUnlessUGotMeMyCode (1)
- AssiamahS (1)
Top Labels
Issue Labels
Pull Request Labels
Packages
- Total packages: 2
- Total downloads: unknown
-
Total dependent packages: 0
(may contain duplicates) -
Total dependent repositories: 0
(may contain duplicates) - Total versions: 2
- Total maintainers: 1
pypi.org: openvioce
This package is used for security research and demonstrations. It might contain dangerous code snippets. Do not run.
- Homepage: https://github.com/myshell-ai/OpenVoice
- Documentation: https://openvioce.readthedocs.io/
- License: Apache v2
-
Latest release: 10.3.2
published almost 2 years ago
Rankings
Maintainers (1)
pypi.org: testopenvoice
This package is used for security research and demonstrations. It might contain dangerous code snippets. Do not run.
- Homepage: https://github.com/myshell-ai/OpenVoice
- Documentation: https://testopenvoice.readthedocs.io/
- License: Apache v2
-
Latest release: 4.3.6
published almost 2 years ago