OpenVoice
OpenVoice is an instant audio cloning library that can generate speech in multiple languages and accents by copying reference audio. V1 and V2 versions are suitable for commercial use under the MIT license; they provide detailed style control over emotion, accent, rhythm, and intonation. With the V2 version, it offers better audio quality and local multilingual support for Korean with English, Spanish, French, Chinese, Japanese.
myshell-ai · Voice & Text-to-Speech
Common commercial products in this category: ElevenLabs, Amazon Polly, Google Cloud Text-to-Speech
- By correctly cloning the reference tone, you produce speech in different languages.
- You control sound style with emotion, accent, rhythm, pause and intonation parameters
- You do zero shot (zero-shot) interlingual audio cloning between languages not found in the training data set
- • Last update over 1 year ago
- • NeutralHacker News
OpenVoice: Versatile Instant Voice Cloning
“> This repository is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License, which prohibits commercial usage. MyShell reserves the ability to detect whether an audio is generated by OpenVoice, no matter whether the watermark is added or not.…”
- • NeutralHacker News
OpenVoice: Instant Voice Cloning
“There's a difference from starting the project by using OpenVoice vs hiring an actor for 90% of the work but then cloning their voice because you can' be bothered to reschedule the same actor for creative changes. But if you start that project by making a voice sound like Morgan…”
Verified against README · Oct 26, 2026 · source
My note
Alternative pages
More in: Voice & Text-to-Speech
- GPT-SoVITS★ 64,315 · 12 days ago
- VoxCPM★ 40,871 · 23 days ago
- RVC★ 38,971 · 2 mo ago
- Pixelle-Video★ 29,593 · 4 mo ago
- Chatterbox TTS★ 27,447 · 3 mo ago
- ebook2audiobook★ 20,469 · 25 days ago