一行代码没写，我用AI做了一个可以收费产品
<div class="ce-block ce-block--focused" data-id="aeKUdWjO0z" ><div class="ce-block__content">
<div class="ce-paragraph cdx-block ce-paragraph--left">这是我第一次尝试完全依靠 AI 编程工具，从零到一开发一款产品。整个过程中，我自己一行代码都没有写。</div>
</div>
</div><div class="ce-block ce-block--focused" data-id="r9nT1hlHjo" >
<div class="ce-block__content">
<div class="ce-paragraph cdx-block ce-paragraph--left">转写模型使用的是 Qwen ASR，GPU 算力来自 Vast.ai。Vast.ai 的消费级 GPU 虽然价格便宜，但想把它做成稳定、可靠的在线服务，并不是一件容易的事。</div>
</div>
</div><div class="ce-block ce-block--focused" data-id="Wy9ilx3CQa" >
<div class="ce-block__content">
<div class="ce-paragraph cdx-block ce-paragraph--left">为了兼顾成本与服务稳定性，我借助 Codex 放弃了官方的 Serverless 方案，从零构建了一套 GPU 实例调度系统。</div>
</div>
</div><div class="ce-block ce-block--focused" data-id="ttI9ZC08uJ" >
<div class="ce-block__content">
<div class="ce-paragraph cdx-block ce-paragraph--left">这个过程中踩了很多坑，但非常值得。如果没有 AI 的帮助，我估计至少需要 3 个月才能把这件事做好，而现在只用了不到两周——当然，对很多大佬来说，这个速度可能依然不算快。</div>
</div>
</div><div class="ce-block ce-block--focused" data-id="29KQtwT-9u" >
<div class="ce-block__content">
<div class="ce-paragraph cdx-block ce-paragraph--left">接下来，郑重向大家介绍一下我的新产品：PennyScribe。</div>
</div>
</div><div class="ce-block ce-block--focused" data-id="WG08xhqfWX" >
<div class="ce-block__content">
<div class="ce-paragraph cdx-block ce-paragraph--left">PennyScribe 是一款面向 AI Agent 和开发者的音频转写服务，可以将音频、视频中的语音快速转换为结构化文本，再交给 Agent 完成内容总结、知识提取、信息检索和自动化处理。</div>
</div>
</div><div class="ce-block ce-block--focused" data-id="kpcpiwo2ic" >
<div class="ce-block__content">
<div class="ce-paragraph cdx-block ce-paragraph--left">如果你曾经让 ChatGPT 或 Claude Code 处理音频转写任务，可能会发现它们经常需要先下载并运行 Whisper。这不仅会让处理时间变得漫长，还可能因为设备性能不足或网络问题而中断。</div>
</div>
</div><div class="ce-block ce-block--focused" data-id="VQTm6JDd0Z" >
<div class="ce-block__content">
<div class="ce-paragraph cdx-block ce-paragraph--left">这时，一个对 Agent 友好的云端语音转写服务就能派上用场。尤其是在需要批量处理大量音频时，云端多台 GPU 并行处理的优势会更加明显。</div>
</div>
</div><div class="ce-block ce-block--focused" data-id="l5XJ11oQ3o" >
<div class="ce-block__content">
<div class="ce-paragraph cdx-block ce-paragraph--left">在测试过程中，我发现 Qwen ASR 的文本转写效果非常出色，但 Qwen ForcedAligner 生成时间戳的效果并不理想。去除背景音乐和环境噪声后会有所改善，但这也会增加处理流程的复杂度和计算成本。</div>
</div>
</div><div class="ce-block ce-block--focused" data-id="5QkdKElrgl" >
<div class="ce-block__content">
<div class="ce-paragraph cdx-block ce-paragraph--left">因此，PennyScribe 现阶段决定先专注于一件事：把语音转写成高质量的纯文本。</div>
</div>
</div><div class="ce-block ce-block--focused" data-id="Btz95WaM46" >
<div class="ce-block__content">
<div class="ce-paragraph cdx-block ce-paragraph--left">虽然它暂时不适合视频字幕制作，但如果你需要将访谈、播客、通话或课程录音转换成干净的多语言文本，再交给应用程序或 AI 工作流继续处理，那么 PennyScribe 会是一个非常合适的搭档。</div>
</div>
</div><div class="ce-block ce-block--focused" data-id="ebHCqTLaIc" >
<div class="ce-block__content">
<div class="ce-paragraph cdx-block ce-paragraph--left">PennyScribe 提供 CLI、API 和 MCP，对 AI Agent 原生友好。</div>
</div>
</div><div class="ce-block ce-block--focused" data-id="uhv_5Y8u8l" >
<div class="ce-block__content">
<div class="ce-paragraph cdx-block ce-paragraph--left">这也是我对未来新产品形态的一点思考：产品不仅要方便人使用，也应该让 AI 能够轻松发现、理解和调用，而不是把所有能力都封闭在 UI 里。</div>
</div>
</div><div class="ce-block ce-block--focused" data-id="Nb6mWChzCN" >
<div class="ce-block__content">
<div class="ce-paragraph cdx-block ce-paragraph--left">目前，GPU 调度效率和转写吞吐量仍有很大的优化空间。接下来我会继续优化架构、降低成本，并进一步压缩最终价格。</div>
</div>
</div><div class="ce-block ce-block--focused" data-id="8lsw4AD4tn" >
<div class="ce-block__content">
<div class="ce-paragraph cdx-block ce-paragraph--left">当然，我也不确定这件事是否还有足够大的商业空间——毕竟市面上已经有很多成熟的语音转写产品。但我依然想把它做出来，看看一个真正面向 AI Agent 设计的转写服务，能够走多远。</div>
</div>
</div><div class="ce-block ce-block--focused" data-id="gxvhO1UUY9" >
<div class="ce-block__content">
<div class="cdx-block image-tool image-tool--filled ">
<div class="image-tool__image">
<div class="image-tool__image-preloader" style=""></div>
<img id="aimg_gxvhO1UUY9" class="image-tool__image-picture _zoom" src="https://aiz123.com/data/attachment/forum/202608/15/094155gv94amlrnj91bbro.webp" title="" alt="" data-aid="1"/>
</div>
<div class="cdx-input image-tool__caption" data-placeholder=""></div>
</div>
</div>
</div><style type="text/css">
.ce-block {
margin-bottom: 20px;
}
.ce-block__content,.ce-toolbar__content {
/* max-width:calc(100% - 50px) */
margin-left: auto;
margin-right: auto;
}
.ce-paragraph {
line-height: 1.6em;
outline: none;
text-indent: 2em;
font-size: 16px;
}
.ce-paragraph--right {
text-align: right;
}
.ce-paragraph--center {
text-align: center;
}
.ce-paragraph--left {
text-align: left;
}
.ce-paragraph--justify {
text-align: justify;
}
.ce-paragraph-text-indent {
text-align: justify;
}
.ce-paragraph:empty::before{
content: attr(data-placeholder);
color: #707684;
font-weight: normal;
opacity: 0;
}
/** Show placeholder at the first paragraph if Editor is empty */
.codex-editor--empty .ce-block:first-child .ce-paragraph:empty::before {
opacity: 1;
}
.codex-editor--toolbox-opened .ce-block:first-child .ce-paragraph:empty::before,
.codex-editor--empty .ce-block:first-child .ce-paragraph:empty:focus::before {
opacity: 0;
}
.ce-paragraph p:first-of-type{
margin-top: 0;
}
.ce-paragraph p:last-of-type{
margin-bottom: 0;
}
.svg-icon {
width: 1em;
height: 1em;
}
.svg-icon path,
.svg-icon polygon,
.svg-icon rect {
fill: #4691f6;
}
.svg-icon circle {
stroke: #4691f6;
stroke-width: 1;
}
</style><style type="text/css">
.ce-block {
margin-bottom: 20px;
}
.ce-block__content,.ce-toolbar__content {
/* max-width:calc(100% - 50px) */
margin-left: auto;
margin-right: auto;
}
.image-tool {
--bg-color: #cdd1e0;
--front-color: #388ae5;
--border-color: #e8e8eb;
}
.image-tool__image {
border-radius: 3px;
overflow: hidden;
margin-bottom: 10px;
}
.image-tool__image-picture {
max-width: 100%;
vertical-align: bottom;
display: block;
margin-left: auto;
margin-right: auto;
}
.image-tool__image-preloader {
width: 50px;
height: 50px;
border-radius: 50%;
background-size: cover;
margin: auto;
position: relative;
background-color: #cdd1e0;
background-position: center center;
}
.image-tool__image-preloader::after {
content: "";
position: absolute;
z-index: 3;
width: 60px;
height: 60px;
border-radius: 50%;
border: 2px solid #cdd1e0;
border-top-color: #388ae5;
left: 50%;
top: 50%;
margin-top: -30px;
margin-left: -30px;
animation: image-preloader-spin 2s infinite linear;
box-sizing: border-box;
}
.image-tool__caption::before {
position: absolute !important;
content: attr(data-placeholder);
color: #707684;
font-weight: normal;
display: none;
}
.image-tool__caption:empty::before {
display: block;
}
.image-tool__caption:empty:focus::before {
display: none;
}
.image-tool--empty .image-tool__image {
display: none;
}
.image-tool--empty .image-tool__caption, .image-tool--loading .image-tool__caption {
display: none;
}
.image-tool .cdx-button {
display: flex;
align-items: center;
justify-content: center;
}
.image-tool .cdx-button svg {
height: auto;
margin: 0 6px 0 0;
}
.image-tool--filled .cdx-button {
display: none;
}
.image-tool--filled .image-tool__image-preloader {
display: none;
}
.image-tool--loading .image-tool__image {
min-height: 200px;
display: flex;
border: 1px solid #e8e8eb;
background-color: #fff;
}
.image-tool--loading .image-tool__image-picture {
display: none;
}
.image-tool--loading .cdx-button {
display: none;
}
/**
* Tunes
* ----------------
*/
.image-tool--withBorder .image-tool__image {
border: 1px solid #e8e8eb;
}
.image-tool--withBackground .image-tool__image {
padding: 15px;
background: #cdd1e0;
}
.image-tool--withBackground .image-tool__image-picture {
max-width: 60%;
margin: 0 auto;
}
.image-tool--stretched .image-tool__image-picture {
width: 100%;
}
.image-tool__caption {
text-align: center;
font-size: 14px;
color: #a3a3a3;
}
@keyframes image-preloader-spin {
0% {
transform: rotate(0deg);
}
100% {
transform: rotate(360deg);
}
}
</style><style type="text/css">
.inline-code {
background: rgba(250, 239, 240, 0.78);
color: #b44437;
padding: 3px 4px;
border-radius: 5px;
margin: 0 1px;
font-family: inherit;
font-size: 0.86em;
font-weight: 500;
letter-spacing: 0.3px;
}
</style>
页:
[1]