TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Ask HN: Hey Podcasters, do you use AI to optimize your workflow?

2 点作者 andygrunwald超过 1 年前
I am the host of a German-speaking software engineering podcast (https:&#x2F;&#x2F;engineeringkiosk.dev&#x2F;). This is a side project, and publishing one episode every week is challenging. Primarily if you target an evergreen strategy and not a news podcast.<p>Things like preparing a topic, recording, audio editing, writing shownotes&#x2F;links&#x2F;chapters, marketing (social media posts), and maybe editing reels&#x2F;shorts. This can quickly consume ~8h per week.<p>We looked into the usage of AI with the goal of reducing the time spent.<p>Right now we are using https:&#x2F;&#x2F;www.assemblyai.com&#x2F; to generate transcripts. This helps us a lot because we often ask ourselves, &quot;Didn&#x27;t we talk about X in some episodes already?&quot; - DUe to transcripts, we can easily search it.<p>We are experimenting with https:&#x2F;&#x2F;podsqueeze.com&#x2F; to auto-generate chapters, show notes, auto-extract links etc. - In the end, this seems to be a service that generates transcripts and sends them to ChatGPT with a few custom prompts - We don&#x27;t use the full service, but might end up with our own workflow doing the same. Still a good inspiration for now.<p>When recording is going wrong and we only end up with one audio track (vs. 1 audio track per speaker), we use https:&#x2F;&#x2F;auphonic.com&#x2F; to normalize the audio loudness, etc. This service is doing a pretty good job.<p>Right now, we are playing around with the automatic removal of filler words (like &quot;ehms&quot;) in the audio file with the help of a transcript. The challenge here is that we record in German. Many AI&#x27;s don&#x27;t support the German language as well as the English one. Time will tell.<p>However, we can say the transcripts had the biggest improvement in our workflow - The speed up writing the show notes a lot!<p>How do you use AI to speed up &#x2F; get support for your podcasting workflow?

2 条评论

nonrandomstring超过 1 年前
Yes and no<p>For Cybershow [0] we love to use AI images, from a variety of generators, because it&#x27;s nice to have quick, catchy iconic pictures that help listeners remember&#x2F;search the episodes visually.<p>Also most of the main cast channels now do great transcription, and our audio is clear, so that&#x27;s one more job that&#x27;s automatically done for us these days by &quot;AI&quot;.<p>In the production and audio domain there&#x27;s very little that &quot;AI&quot; can do better than an experienced writer and editor, imho as a half-decent writer&#x2F;editor :).<p>A lot of editing is moment by moment decision making that just requires a good ear. &quot;AI&quot; can&#x27;t tell me if something a guest says is ambiguous, or sounds a bit poorly evidenced etc.<p>Maybe one tool I&#x27;d maybe use if it existed is a &quot;fluff remover&quot; for &quot;ummmm, like, well... y&#x27;know, ummmmm, literally... like....&quot;<p>But I wouldn&#x27;t trust it not to butcher the audio and leave things in an irrecoverable (no undo path) state that only gets spotted in the mastering stage.<p>Otherwise, many &quot;intelligent&quot; plugins already have built in clever DSP features these days, for things like noise reduction, silence removal, level matching.<p>Scripting things is the key... and Audacity is a dream for this!<p>For planning&#x2F;organisation I use emacs org-mode which is fine for capturing notes, linking resources and pulling it all together into a script or talking-points list for recording.<p>For an amateur show we don&#x27;t need much more quality than this.<p>[0] <a href="https:&#x2F;&#x2F;cybershow.uk&#x2F;" rel="nofollow noreferrer">https:&#x2F;&#x2F;cybershow.uk&#x2F;</a>
jprete超过 1 年前
I’m confused as to why you need to pay an AI service to normalize audio volume? Isn’t this something basic audio tools would do for free?