The full gallery
Tech stack
29 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
Generate 768p AI videos from text or images with native audio in seconds.
plutozc · V2EX
做了两个 MiniMax H3 AI 视频生成入口 最近在用 MiniMax H3 做一些 AI 视频的快速试验，发现自己常在文字、图片参考、画幅和时长之间来回切，所以顺手做了两个偏不同工作流的入口，想听听大家会不会觉得这种拆分有用。 一个是偏快速迭代的版本： [H3 Max]( https://h3-max.org) 主打从文字或参考图生成短视频，重点放在快速生成 768p 片段和提示词里的画面、镜头、音频描述。 另一个是功能更完整的工作台： [MiniMax H3 Max]( https://minimaxh3max.org) 同样支持 text-to-video 和 image-to-video ，可以按需要选 768p 、2K 或 4K ，也能调时长和横竖画幅。 目前都还是刚上线的个人项目： - 文字或图片作为起点生成视频 - 一个提示词里写画面、动作、镜头和声音方向 - 方便先快速出一个版本，再回头改提示词 两站都不是官方站，生成结果和速度会受模型设置及队列影响。现在页面和体验还在继续补，尤其想听听大家更在意“快点出第一版”，
Generate AI images, videos, and audio with the best AI models — Kling, Veo, Seedance, Nano Banana, ElevenLabs, and more. All in one platform. No skills needed. Try free.
@sashakeyo · X
Generate videos, images, music, code, and 3D objects using frontier AI models.
laurentiurad · HN
I built and run several SaaS platforms: - https://dave-bot.com -> a full-stack AI platform where you can generate videos, images, music, code, 3d objects with frontier Gen AI models. - https://headsnap.io -> a platform that you can generate images of yourself based on 4 selfies. - https://quantiq.live -> a service providing financial and historical data for stocks, as well as government trades. - https://aivestor.tech -> an AI agent that picks small/midcap stocks and trades them using Alpaca API
API and MCP server that transcribes social videos and podcasts with timestamps.
chandler_casey · Product Hunt
TranscriptFetch Video and audio transcripts, structured for AI
