Proud Member of NVIDIA Inception Program

Taiwanese AI TTS Voice Synthesis

A platform combining world-first Taiwanese AI speech synthesis and facial animation technology

Sample video

Supports both animated and real-life images

※ The voice and image of Tang Feng are used with her personal permission.
Additional Information ：
This app uses AI to automatically generate Taiwanese speech and applies realistic mouth movements to a face image, producing a vivid animation. Input can be in either Tailo romanization or Chinese characters. Suitable for education, entertainment, social media, and PR.

▸ The voice model used is a proprietary AI TTS system that handles tone accuracy and emotional expression.
▸ With WavLip technology, perfect synchronization between speech and mouth movements is possible.

Key Features

Natural Taiwanese Speech

Using cutting-edge AI voice synthesis, this platform produces smooth and natural Taiwanese pronunciation

Realistic lip movement

Achieve natural lip sync perfectly aligned with audio using WavLip technology

Custom avatar

Use any image to generate expressive animations with WavLip technology

자주 묻는 질문

Key Features

Using cutting-edge AI voice synthesis, this platform produces smooth and natural Taiwanese pronunciation

Realistic lip movement

Achieve natural lip sync perfectly aligned with audio using WavLip technology

Custom avatar

Use any image to generate expressive animations with WavLip technology

대만어 AI를 TTS STT 번역 LLM으로 연결

음성합성 음성인식 번역 대화를 한 흐름으로 배치해 교재 자막 현장 기록 기업 PoC로 이어지기 쉽게 합니다.

기업・교육 도입 상담 대만어 TTS 대만어 STT 대만어 번역 대만어 LLM