Multimodal Browser AI with Transformers.js for Images and Speech
中文摘要
使用 Transformers.js 实现浏览器端图像与语音等多模态 AI，突破纯文本限制，满足实际应用需求。
English Summary
Use Transformers.js to build multimodal browser AI for images and speech, expanding beyond text to meet real-world needs.
Original Excerpt
Most browser AI tutorials cover text because it is a natural starting point, but the applications people actually want to build are rarely text-only.