完整作品展
技术栈
60 projects
Sonara turns text into natural, expressive speech. Studio-grade voices for narration, assistants, and storytelling.
@Dev_NexaLabs · X
NOTE: we're still in the early phase something is not yet finish.
ScreenDub 可快速录制屏幕并生成AI配音脚本，支持多语言教程和产品演示。
@me_using_x · X
Do you need a product demo or wanna make tutorial/help videos? Your problem is solved for ever now! Try: PS: I am the developer who built this and I am self promoting it via this thread. 😀
将文档和电子书转换成自然语音的有声书。
@coder_zi · X
Clipifai converts e-books to audiobooks say you have a few books in mind to read, but haven't really had the time to read them, you could just convert them into audiobooks and listen to them on the go...
混合鸟鸣和自然音创建个性化白噪音助眠和专注。
zhuawadao · V2EX
做了一个*鸟鸣*主题的白噪音网站：可以模拟自然环境、还有猜鸟游戏 大家好，最近做了一个小网站：**Bird Song 鸟鸣** 地址： https://bird-song.org 它主要是一个鸟鸣主题的+自然背景音网站，适合当作专注、放松、助眠时的背景声音。 目前有几个功能： - 鸟鸣混音器：选择不同鸟类，调节音量，生成自己的自然声景 - 自然背景音：可以混入森林、小雨、海浪、春风等环境音 - 鸟类库：可以按物种浏览鸟鸣和相关介绍 - 猜鸟游戏：听声音猜是哪种鸟 我做这个网站的初衷是，平时工作或者休息时会听白噪音，但很多白噪音网站比较机械，我也没找到可以自选鸟类的白噪音网站，自己就来搞了一个，嘿嘿 截图：  
通过实时音准反馈和渐进式练习学习吹口哨。
x1shir · V2EX
HowToWhistle：像唱 KTV 一样练习吹口哨 一直想提高吹口哨技巧，搜了一圈发现网上的教程都是文字和视频，练的时候根本不知道自己吹得对不对。 想到可以像 KTV 一样，有个音轨对比，于是干脆自己搓了一个练习网站：[https://howtowhistle.org/]( https://howtowhistle.org/) 核心思路是用浏览器的麦克风做实时音高检测，你对着麦克风吹，页面会显示你当前的音高和目标音的偏差，类似 KTV 唱歌时的实时评分。功能大概有： - 实时音高反馈，能看到自己吹的是哪个音、偏高还是偏低 - 从单音长音开始的渐进式练习，到音阶、再到简单旋律 - 纯前端实现，声音不上传，无需注册 目前还比较简陋，欢迎大家试玩和提建议。
Wavelength turns your calls and meeting transcripts into a living process map as you talk. Speak the flow, watch it draw itself, then share it.
@WavelengthFlow · X
在30+个社交平台监测购买信号，用AI评分销售线索
@TBerguer · X
The goal is to find theese guys 😋
24/7 lofi study beats, coding music, and EDM focus radios — plus iconic scenes reimagined and luxe mansion rooms. Hosted by Scrappy the Synaptic Cat.
@SynapticUtopia1 · X
Generate emotionally expressive speech with ProsodyAI — now with OpenAI and Google Gemini voices. 59 languages, 8 emotion presets, zero-shot voice cloning, 100,000 free characters
@prosodyai · X
ProsodyAI — AI text-to-speech that performs, not just pronounces. Tell it how to sound ("warm, slow, like a bedtime story") and it does. Three engines in one app: ours, OpenAI and Gemini. 100,000 characters free every month, voice cloning included.
