The full gallery
Tech stack
27 projects
Transcribe audio and video files to text with AI-generated summaries.
@Mahima_Akkina · X
Yes, you can check - It's a tool used to convert both and video into text and summaries
API and MCP server that transcribes social videos and podcasts with timestamps.
chandler_casey · Product Hunt
TranscriptFetch Video and audio transcripts, structured for AI
Free transcription of audio and video to text in 98 languages with multiple export formats.
ScribeToAny — AI 音视频转录与字幕生成工具，支持说话人识别（区分发言人）、多语言翻译与字级高精度时间戳，长音频高速转文字，一键导出 SRT/VTT/TXT 格式 — 免费试用
Let someone explain it out loud. Please Ramble returns their answer as a transcript organized by your questions.
@markproxa · X
Side project launched today:
Speak for 60 seconds. Get a complete multi-format content bundle: a ready-to-publish LinkedIn carousel PDF, a formatted LinkedIn text post, and an X (Twitter) thread. No Canva, no
@Upasanax · X
A voice-first engine that turns raw audio memos into a LinkedIn carousel PDF, post, and X thread in 2 minutes.
AI transcription for video and audio with 40+ tools for captions, summaries, translations, and image upscaling.
@indrapurnomos · X
Check out what I just built with Lovable!
Browse indexed AI Engineer YouTube talks with summaries and timestamps.
strickvl · HN
A searchable, timestamped index of 1,124 AI Engineer talks
Convert audio and video files to text with speaker labels and timestamps, no signup required.
zxhywork · V2EX
SayScribe AI - 音频转文字的在线工具 花了几周搞了一个基于 OpenAI Whisper 的 AI 转录工具 **[SayScribe]( https://sayscribe.org)**，目前 5 个工具全部免费，每天 3 次无需注册。上线前请 SEO 专家做了一轮诊断，踩了不少坑，分享出来给同样在做工具站的 V 友参考。 --- ## 做了什么 核心工具是 **[Audio to Text Converter]( https://sayscribe.org)**（主页），上传音频/视频文件，AI 自动转成带 speaker labels 和时间戳的文字稿。选这个词的原因是：Google 第一页有个 DR 只有 10 的小站排第三，KD 才 20.2 ，链接预算只要 15-35 个引用域就能进前十——典型的弱盘面蓝海。 然后在主页基础上拆了 4 个子工具，每个打一个独立搜索词： - **[MP3 to Text]( https://sayscribe.org/mp3-to-text)** — 只转 MP3 。KD 41.7 比主页难一些，但
Read and publish investment theses, financial analysis, and SEC filing research in a social platform.
@goglidesfinance · X
I swear to God, I vibe-coded this entire platform because I wanted one place to publish my endless $DVLT rabbit holes. 😂 Now it’s becoming a finance social platform where people can read investment theses, financial breakdowns, and SEC filing analysis, and eventually publish their own research. I have a ton of ideas. The only problem: I’m a one-man army with limited resources. Sadly, I can’t dilute shareholders to raise capital. 😂 Sometimes I wish GoGlides were already a public company. P.S. You can sign up for free, but publishing, commenting, and participating in the social features currently require a subscription. Those subscriptions help me keep the platform running and continue building it.
Learn code skills with flashcards, quizzes, and AI tutoring built on memory science.
@mkappworks · X
I am building lets connect
Transcribe audio and video to text entirely on your device, with no uploads and no account needed.
mikicat · V2EX
[分享创造] 做了一个纯本地离线运行的语音转文字工具： Free Local Transcription 大家好， 平时经常有一些包含敏感信息或者不想上传到第三方服务器的音频（如会议记录、采访、个人备忘等）需要转文字。市面上很多工具本质上都是套壳调用云端 API ，既有数据泄露风险，长期用也有不小的 API 成本。 结合自己的模型优化经验，我做了一个完全基于本地算力运行的音频转文字工具：Free Local Transcription 🔗 体验地址： https://freelocaltranscription.com/ 主要特点 100% 本地运行 / 零数据外传：推理完全在设备本地完成，音频文件不会上传到任何服务器，断网状态下也能保证隐私与安全。 无需 API Key / 完全免费：依靠本地算力运行，不需要填 API Key ，也没有按分钟计费的困扰。 即开即用：界面保持极简，拖入音频即可直接进行本地转写。 目前的权衡与折衷 相比直接走云端高性能 GPU 集群，本地推理的速度会直接取决于用户的设备配置与硬件性能，老旧设备上可能存在内存占
Study developer topics like Kubernetes, AI, and Linux using spaced repetition flashcards.
Agoreddah · HN
I built Gnoseed – free flahscards to learn K8s, DevOps, AI and more
