Seed Audio — AI 语音生成与在线音乐创作工具

@thepaulwakim · X

I've been building the companion creator platform for my podcast app @PodSipsApp . I built the creators platform for 2 reasons: 1. To help podcasters gather all of a show's data in one place. RSS downloads come through an RSS prefix server I built and all your stats from YouTube and Spotify. 2. To give that aggregate data to AI agents, whether that is Codex, Claude Code, Hermes, OpenClaw, or whatever else you use. The agent Skill file and API, and API docs on the platform work together to give your agent access to all your show's data in one place. It can answer questions about how the show is doing, build custom data visualizations, work those visualizations into a sponsorship deck, or do anything else you want done with your data. The API also surfaces anonymized summaries of what listeners are asking PodSips about while they listen to your episodes. You get to see which moments people wanted explained and which topics they wanted more of. Podcasters can sign

hakunin · HN

MyFirst.News – AI-generated podcast for curious kids

音频转文字工具 — AI 音频转文字，快速、精准、安全的转写服务

schillingderek · HN

Building Table Canon, an AI Campaign Memory Engine for TTRPGs

victords · HN

I was interested in learning more about reverse image search, so I built audioguide.london. It’s a simple image search where you take a photo of an artwork in a gallery, tries to ID it and returns a pre-generated audio and a link to the museum website. The audios were all generated locally, essentially looking at the contents of the website, running it through a LLM to generate a script and Kokoro for TTS. I’ve built it as an app for myself almost a year ago, so I deployed it as a vibe coded web

Voor AI — 浏览器端 AI 创作平台，支持视频、图片和音频生成、编辑与工作流协作，统一管理共享积分

@myrrakle · X

@the_davey · X

People waste time in apps/feeds hunting key info they don't want to miss. I hear posts aloud. Saves hrs/wk via posts, articles, mkt signals, emails, SaaS alerts & growth tips daily. @AnnouncrFM: spoken audio layer for life. In Beta!

MRNiu · V2EX

做了一个免费的声音表达分析工具，录 5–15 秒就能看到反馈 最近做了一个小工具：Voice Impression Checker 。 它想解决的问题很简单：我们经常知道自己“说了什么”，却不太清楚这段话听起来是什么感觉。 打开网站后，只需要录制 5–15 秒自然说话的声音，工具会从这一次录音中分析： - 清晰度、语速、稳定性、能量和声音变化 - 听感上的温暖、自信、亲和力和参与感 - 这次表达做得比较好的地方 - 下一次录音可以尝试改进的一件事 网站还提供了 Rate My Voice 模式，可以针对面试回答、演讲开场、自我介绍和日常交流等场景进行练习。 需要特别说明的是，它不是声音好坏评判，也不会通过声音判断性格或身份。所有结果只描述当前这一次录音的表达效果，更适合用来反复练习和比较不同说法。 目前网站免费使用，不需要注册账号，录音仅用于生成当前报告，不会保存。 网站地址： https://voiceimpressionchecker.com/ 这是一个刚完成的早期版本。如果你愿意体验，欢迎告诉我结果是否容易理解，以及你最希望