The full gallery
Tech stack
4 projects
AI voice model that handles revenue calls with natural conversation through interruptions and overlapping speech.
vatsalaggarwal · HN
Production duplex speech model for revenue calls
Transform text into podcast episodes with AI-generated voices
@motyar · X
🎙️ Idea → Audio
Create an AI clone of your voice and generate speech from any text.
Voice Clone - AI 驱动的语音克隆平台 — 用户只需录制或上传一段音频，系统便能在几秒内生成一个属于用户自己的声音模型。支持任意文本的语音生成，听起来自然流畅，几乎接近真人语音。整个流程无需复杂设备，也不需要技术背景，真正实现“用几句话训练出自己的声音” - [GitHub 仓库](https://github.com/tanchaowen84/voice-clone)
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。
