Voice & audio
Kokoro-TTS
Natural-sounding text to speech you can also use commercially
★ 3.4k
April 2025
Apache-2.0
Voice & audio
What it does
Type text and get spoken audio back, using Kokoro - a comparatively small model that still produces clear, natural output and runs quickly. Japanese is supported. The model is published under Apache-2.0, so the audio can be used in commercial work, which is unusual among free voice generators. Long passages are more reliable split into chunks, Japanese readings of names and technical terms can come out wrong, and text is uploaded to the host's servers.
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 difficultyFor advanced users
- Command lineNot required
- API keyNot required
- Sends data onlineYes
Judged automatically from the project's own metadata. Always confirm on the official page.
Kokoro-TTS FAQ
- Do I need to install anything or write code to use Kokoro-TTS?
- No install needed — it runs in the browser.
- Does Kokoro-TTS work on a phone?
- No. It needs a computer.
- Can I use Kokoro-TTS commercially?
- The licence is Apache-2.0, which permits commercial use. Conditions such as keeping the copyright notice still apply, so read the licence text before shipping it inside something.
How it compares
The conditions that decide whether you can actually use it, side by side.
| Tool | Command line | API key | Sends data out | Phone | Commercial use |
|---|---|---|---|---|---|
| Kokoro-TTS (this page) | Not needed | Not needed | Yes | No | Yes |
| Edge-TTS-Text-to-Speech | Not needed | Not needed | Yes | No | Not verified |
| styletts2 | Not needed | Not needed | Yes | Yes | Not verified |
| text-to-speech | Not needed | Not needed | Yes | Yes | Not verified |
"Sends data out" means your input is uploaded to someone's server. Pick "No" when the material cannot leave your organisation.