Creative Tools5 days ago
Sonara Music
Stream independent music and live radio with Sonara dark music player.
@Saptak_Mondal_ · X
The full gallery
Tech stack
14 projects
Stream independent music and live radio with Sonara dark music player.
@Saptak_Mondal_ · X
Send a song. Get one back.
@NamyMadeline · X
blind song swapping website + app where u send a song and get one back from a stranger !!
Upload and manage music tracks from Suno and other sources in a studio.
@GrimfelOfficial · X
Checked it out looks very similar to my studio and I'm not saying thats a bad thing because I vibe coded mine Good direction, will it remain watermark free on studio inputs?
Generate AI short videos from text or images with integrated sound design and camera transitions.
zhuzhifen · V2EX
分享一个用 MiniMax H3 Max 做短视频的在线工作台：支持原生音频 大家好，我们做了一个 H3 Max Generator： https://h3maxgenerator.org/ 这是一个浏览器里的短视频生成工作台，基于 MiniMax H3 Max ，支持： - 文生视频、图生视频 - 可选首帧和尾帧，控制镜头过渡 - 在同一段提示词里描述画面、镜头、对白、环境声、音乐和音效 - 5 / 10 / 15 秒，480P / 768P ，以及横屏、竖屏、方形等比例 我们做它的初衷，是希望把“画面运动”和“声音设计”放进同一个可反复迭代的流程里，而不是在多个工具之间来回拼接。 网站里放了几个示例，分别测试了镜头跟拍、首尾帧过渡、人物连续性、同步声音、统一艺术风格和多步骤变形。 目前生成视频需要登录并消耗 credits 。欢迎大家帮忙体验，尤其想听听对运动稳定性、音画同步、提示词组织方式和整体工作流的反馈。 谢谢！
A shared music room for friends. Everyone hears the same track at the same second, one person holds the aux, and anyone can take it off them.
@theeasyway6 · X
Generate 2K AI videos (5-15 sec) from text, images, and audio references with native stereo audio.
Convert audio and video to searchable transcripts with AI.
giang_taira · Product Hunt
GPT Transcribe Turn recorded speech into reviewable text
Transcribe and summarize YouTube videos, podcasts, PDFs, and MP3/MP4 files with AI.
sipsip.ai — 支持30+平台视频AI转录并提取摘要，订阅RSS可以每天发送早报
Stream AI-generated music created with Claude, designed for coding sessions.
@ajferanz · X
ᴛʜɪs sᴏɴɢs ᴀʀᴇ ғᴏʀ 𝓿𝓲𝓫𝓮 𝓬𝓸𝓭𝓲𝓷𝓰 ʟɪᴛᴇʀᴀʟʟʏ @jeffgwoah is a claude rapper not a gpt wrapper check it out on
Transcribe audio and video recordings into searchable, editable text.
lavande · V2EX
做了一个语音转文字的工具，另加 AI 总结、翻译、提问等（附踩坑记录） 先上链接：[Echoryte]( https://echoryte.com/) 感觉这个网站 vibe coding 的话，感觉手熟的同学可能半天就能搓出来…… 但是我用了一个多月才上线，主要是被 GPT5.6 坑了，当时 5.6 和 fable 前后发布，然后试了试用 fable 5 做的 plan ，然后 5.6 sol 推理开到最大去执行。结果愣是给我干了 33 个小时没停，写了将近 2 万行代码。 但是坑就坑在这，推理开太高，就过度思考了，给我整了很多虚头巴脑的东西出来，什么“门禁”我也不懂，什么合规，一大堆，然后我就不停地删，删了一个月，最后我就跟 GPT 说，我特么是个人小项目，不是大公司，再这么高下去永远上不了线了。然后终于看删的差不多了，上线了！ 欢迎大家试用，轻拍，谢谢！
Split songs into vocals, drums, bass, and instruments with browser-based AI.
gaoheyangnwpu · V2EX
AudioCraft – AI stem splitter and vocal remover with a browser-based mixer I’ve been building AudioCraft as a focused AI music tool for separating songs into useful stems. The main workflow is simple: * upload MP3, WAV, FLAC, or M4A * separate the track into vocals, drums, bass, and other instruments * preview the stems * mute, solo, and adjust individual tracks * create an instrumental version * download individual stems or all stems together AI Stem Splitter https://audiocraft.app/ A
Transcribe audio and video to text, create summaries and captions, and generate speech.
@bydigiwares · X