All models
voice-cloning

OpenVoice v2

MIT

Tone-color cloning + cross-lingual transfer

OpenVoice v2 clones the tone color of a reference speaker and then lets you control style — emotion, accent, rhythm, pauses, intonation — independently. It supports cross-lingual cloning into languages the reference speaker never spoke, and v2 moved to a permissive MIT license.

Hear OpenVoice v2

OpenVoice v2 · Default · Same three scripts across the directory.

Run it yourself

Best for: Tone-color cloning + cross-lingual transfer

Permissive model license: The publisher explicitly permits commercial use of V1 and V2. Voice-conversion weights do not license the reference voice or replacement base TTS engine.

Code: MIT. Weights: MIT (OpenVoiceV2). License sources checked 2026-09-20. Source 1Source 2Source 3

Before you choose: Compare the samples with your own use case. Check the linked documentation for code, weight, and voice license terms.

Details awaiting a fresh review. Hardware figures are estimates unless a benchmark is linked.

Compare with similar

Compare all →
F5-TTSListen side-by-side →LlasaListen side-by-side →XTTS v2Listen side-by-side →

Choose an alternative to hear both models together.

Voices

1 voice
Neutral
Defaultdefault
—

The scripts

Neutral
“The quick brown fox jumps over the lazy dog near the riverbank.”
Emotional
“I can't believe you actually did it. This is incredible!”
Numbers & Dates
“On March 14th, 2025, the team raised $4.2 million at a 38% margin.”

Run OpenVoice v2

pip install openvoice

Sources & setup details

OpenVoice v2 FAQ

Do I need a GPU to run OpenVoice v2?

The directory lists roughly 4 GB of VRAM as a historical estimate. Check the model documentation for your checkpoint and runtime.

Can OpenVoice v2 clone voices?

Yes — OpenVoice v2 supports voice cloning from reference audio.

What license is OpenVoice v2 released under?

OpenVoice v2 is released under the MIT license. Always check the repository for the exact terms — some models license code and weights separately.

What languages does OpenVoice v2 support?

OpenVoice v2 supports English, Spanish, French, Chinese, Japanese, Korean.

Is there a hosted OpenVoice v2 API?

OpenSpeech Cloud is accepting production-access interest for OpenVoice v2, but this model is not currently hosted in Cloud. Use the official repository for current deployment options.