Equipped with state-of-the-art speech synthesis AI

It supports GPT-SoVITS, a state-of-the-art high-precision speech synthesis AI model, enabling speech synthesis with natural intonation.

Supports Japanese and English

It supports speech synthesis in both Japanese and English.

Speech synthesis ith any voice

By inputting a voice file of about 10 seconds, it is possible to perform speech synthesis with any voice.

Supports mutual translation between Japanese and English

It is possible to synthesize Japanese speech while preserving the intonation of English speech.