CoeFont Launches Cross-Language TTS, Enabling Free Conversion of Japanese Voice Recordings into Multilingual AI Voices

3 min readJul 1, 2024


Generate Native-Sounding English AI Voices from Just 5 Minutes of Japanese Voice Recordings

Tokyo, Japan — June 12, 2024 — CoeFont Co., Ltd., the developer of the AI voice platform CoeFont, today announced the general release of its new feature, Cross-Language TTS, which enables the creation of both Japanese and English AI voices from a single Japanese voice recording. The feature is available for free starting today and will be expanded to support Chinese, French, and Spanish in the future.


Overview of Cross-Language TTS

Previously, creating AI voices required users to read specific phrases in each language. However, this method often resulted in inaccurate pronunciation and hindered effective communication.

To address these challenges, CoeFont introduced the Cross-Lingual TTS beta version on June 27, 2023, to a limited number of users for market validation. In response to the overwhelming demand from businesses and individuals seeking multilingual solutions, the company has decided to make the feature generally available.

Case Studies

1. AI Lain

To commemorate the 25th anniversary of the original, Cross-Language TTS was used to generate both Japanese and English AI voices from the Japanese voice recordings made 25 years ago for the anime series “AI Lain.”

2. Norio Aoki, Kawasaki City Council Member

Cross-Language TTS was used to create both Japanese and English AI voices for the website of Kawasaki City Council member Norio Aoki.

Key Features

1.Generate English AI Voices from Japanese Voice Recordings

With Cross-Language TTS, users can record 50 phrases (approximately 5 minutes) of Japanese speech to generate both Japanese and English AI voices in about 3 hours. Support for additional languages will be added in the future.

2.Free Creation

Cross-Language TTS is completely free to use, allowing anyone to create Japanese and English AI voices. AI voices for up to 100 characters can be generated for free. For features such as text-to-speech conversion for text exceeding 100 characters, a Standard Plan subscription is required.

Future Plans

CoeFont plans to leverage Cross-Language TTS technology to develop features that address the challenges of real-time multilingual communication.

About CoeFont

CoeFont is an innovative AI Voice Platform leveraging cutting-edge technology to transform speech into expressive, user-friendly voices. The CoeFont platform offers a versatile suite of solutions, including Text-To-Speech (TTS), Voice Changer, and Cross-Language TTS applications, catering to a wide-range of communication needs. With the CoeFont Voice Hub, users gain access to an extensive library of over 10,000 AI voices, ensuring a wealth of choices to suit any project or presentation. Whether for training sessions, internal announcements, audiobooks, live meetings and streaming, or personal conversations with family and friends, CoeFont provides users with the tools to express themselves effectively in any language.




A global AI Voice Hub, empowering you to use your voice by creating and using digital voices.