OpenVoice v2 with a ready interface

Video memory

10 GB

Setup

~12 min

Access

port 7860

Billing

hourly, in BRL

OpenVoice v2 separates timbre from delivery: you clone someone's voice and still control emotion, pacing and accent on top of it. It is the pick when you need acting, not just reading.

OpenVoice v2 from MyShell — open voice cloning with fine control over emotion, accent and rhythm. Supports PT, EN, ES, FR, ZH, JA, KO via MeloTTS. Ready Gradio UI.

What it is for

• Game and audio-drama characters with controlled emotion
• Cross-language dubbing that keeps the original timbre
• Varied delivery from a single voice sample
• Processing on your machine, no voice data sent to third parties

How to deploy

1. Create your account and add balance (card or Pix, no subscription).
2. In the console, pick the OpenVoice v2 template and a machine — the console hides the ones that do not meet the requirement.
3. In about 12 minutes the setup finishes and the access address shows up in the panel, on port 7860.

Done? Just destroy the machine and billing stops with it. No contract, no minimum commitment.

FAQ

How much video memory do I need?

10 GB is comfortable; larger cards only speed up batch work.

Is it good for dubbing video?

Yes, that is one of its most common uses: keeping the original speaker's timbre across languages.

Can I call it through an API?

Yes, the web interface exposes endpoints you can call from a script or from n8n.

Related templates