The full gallery
Tech stack
60 projects
AI video on autopilot for creators and brands — generate vertical Shorts and long-form YouTube, voice, schedule, and post to TikTok, YouTube, and Reels.
@0xWuki · X
- AI UGC that converts. 🤝 pleasure to connect
AI-powered assistant for YouTube creators. Generate personalized scripts, thumbnails, subtitles, and more, in your unique voice.
@afrinxnahar · X
would love your honest review:
Create personalized AI hug videos from static photos with character consistency.
aihugvideo.app — AI Hug 是最好的 AI 拥抱视频生成网站🤗，可以在几分钟内轻松构建您的 AI 拥抱视频
Generate complete songs from text prompts and lyrics with AI vocals and custom arrangements.
AI audio editor and music generator for editing, shortening, and creating music from text or audio files.
audjust.ai — 智能音频编辑与 AI 音乐生成工具，帮助处理音频文件（智能缩短歌曲、延长音频、寻找完美无缝循环）并从文字描述、歌词或图片生成完整音乐轨道。支持多种风格，内置 MIDI 编辑器、音轨分离、Lo-fi 转换等专业工具。
AI audio agent for generating songs with vocals, isolating stems, converting to MIDI, and mastering tracks.
Gliss — AI Music Agent，用于歌曲生成、翻唱、MIDI 编辑、母带处理与封面艺术；可生成免版税人声与伴奏，并支持精确分轨/元素提取。
Create notes from videos with AI transcription, screenshots, and AI summaries.
lilaiqun · V2EX
受够了视频没听清就反复拖进度条，只考虑音频错别字多，写了个"会看画面"的视频转笔记工具 看视频经常一句话没听清，拖回去重听好几遍还是听不清。试了现有的转写工具，发现它们只用音频——恰恰是我听不清的词，它们也转不对（幻灯片上的术语、代码里的名词，声音里根本猜不出来）。 所以做了 **Vid2notes**：转写时不只听声音，还抽帧看画面。Whisper 转文字，多模态模型拿着字幕对着截图一起读，输出带截图、章节、时间戳和 AI 总结的图文笔记，可导出 Markdown / SRT / VTT 。 支持最长 10 小时的视频，常见格式都行。 技术栈给感兴趣的 V 友：全栈 Cloudflare （ Workers AI 跑 Whisper + GLM ，Rust + FFmpeg 跑在 Containers 里），按视频 MD5 缓存不重复算。 **每天免费 3 个视频**，不用绑卡：[vid2notes]( https://vid2notes.com/) 最想知道的反馈：准确率在你的视频上怎么样，尤其是带幻灯片/代码的教学视频。欢迎拍砖
Browser-based vocal studio for tuning and mixing vocals with AI pitch correction.
@noooder · X
- a browser based vocal editing and mixing tool
Generate full songs from one line of text, or use creator tools like Audio to MIDI and Slowed & Reverb.
AIFlowMusic — AI 音乐生成网站
Generate music, lyrics, and background music from text prompts using AI.
Musefy - AI 音乐制作 — 将提示词转化为 AI 歌曲、歌词和背景音乐
Get a free API key with email to access 500+ Hugging Face models.
@pengsonal · X
500+ Hugging Face models through a single free API no credit card just an email signup 😳 launched on July 3 as a unified gateway for Hugging Face models one API key one endpoint 500+ models what you get for $0: • 500+ open-source models through an OpenAI-compatible API • no separate API keys for different providers • works with Cursor, Claude Code, Hermes, OpenCode, and anything that supports a custom base URL • email signup only setup takes about 2 minutes: 1. Go to 2. Sign up with your email 3. Generate an API key 4. Set your base URL to 5. Choose any model from the catalog and start building a few things worth knowing: • is a third-party gateway, not an official Hugging Face product • the free tier is rate-limited, but the exact limits haven't been published yet • i wouldn't build production apps that depend entirely on a free aggregator what i like is the simplicity instead
AI tool that matches your track's EQ curve to reference songs in the browser.
@pcclubb · X
Check out "SONICSYNC EQ "match engine · v1.0 I just built with Lovable!
