supertonic-3

What it does

Generates speech locally without a network connection, with an emphasis on speed and small footprint. On 23 July 2026 the maintainers announced that the repository would be archived with no further development or official support, and the associated Voice Builder service closed on 31 August 2026. What ended is development, official support and Voice Builder - the published models stay available and still run locally under the OpenRAIL-M licence, and the browser-based demo was still reachable on 31 August 2026. Since nothing will be fixed from here on, pick an actively maintained project such as Kokoro for new work.

Summary based on the project's own description. The Japanese page has a fuller beginner guide: setup difficulty, what to prepare, and a step-by-step start.

Screenshots & visuals

Before you start

• Setup difficultySome setup needed
• Command lineRequired
• API keyNot required
• Sends data onlineYes

Judged automatically from the project's own metadata. Always confirm on the official page.

supertonic-3 FAQ

Do I need to install anything or write code to use supertonic-3?

No install needed — it runs in the browser.

Does supertonic-3 work on a phone?

No. It needs a computer.

Can I use supertonic-3 commercially?

Only under conditions. The page shows OpenRAIL, but the actual terms — the AI model this page runs, or the provider's own terms — attach restrictions. Check the provider's terms before using it at work.

How it compares

The conditions that decide whether you can actually use it, side by side.

"Sends data out" means your input is uploaded to someone's server. Pick "No" when the material cannot leave your organisation.

Other voice & audio tools