sanqianzilanyue/ai-voice-breath-kiss-water

Generative mediaHTML

4.5 Early signal Magnitude out of 10 — how fast interest is growing, not a quality score. Star growth looks organic. Data as of October 1, 2026, 15:54 UTC.

Open on Seismograph Open on GitHub

About the project

A hands-on guide to building a realistic voice for an AI companion: breathing, kisses and water sounds using ElevenLabs, ffmpeg and whisper, with concrete parameters and recipes.

Useful for

Set up a bilingual voice in ElevenLabs via Voice Design from a text description
Build a kiss-sound library from real recordings and mix them in with ffmpeg
Mix a water recording under the voice with peak alignment and fades

README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.

Why it’s trending

27 stars so far today, about 42 expected by the end of the day.
The spike has held for 2 days in a row — not a one-off blip.
The repository is 1 day old and already has 79 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
Top new repositories this week: #192.
About 10 forks a day — people are taking the code.

Stars per day

Bars are daily stars, the line is the usual pace. Red marks spike days.

Numbers

Total stars: 79
Today: 27 · ≈ 42 by evening
Forks: 7
Issues and pull requests: 1
Watchers: 0
Language: HTML
Created: September 30, 2026
Last push: October 1, 2026

Star trust

Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.

These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.

Spotted in

October 1, 2026Top new repositories this week: #192

README badge

Paste it into your README — the badge shows the current magnitude and links to this page.

[![Seismograph](https://gitnova.dev/badge/sanqianzilanyue/ai-voice-breath-kiss-water.svg?lang=en)](https://gitnova.dev/en/r/sanqianzilanyue/ai-voice-breath-kiss-water)

More in this category

7.2
edenfunf/reelmimic
A local tool that analyzes a reference video and generates a new 2D animation in the same style using multiple AI agents (Claude Code or Codex).

Early signalGenerative mediaJavaScript+123 stars today, ≈ 222 by evening
6.9
dmtrKovalenko/fframes
Programmatic video rendering framework in Rust and SVG with GPU acceleration via Skia (Metal/Vulkan) and encoding through ffmpeg. Ships a skill for coding agents to generate videos from text descriptions.

BreakoutGenerative mediaRust+112 stars today, ≈ 236 by evening
5.7
Friedrich-M/UniMate
A unified model for animating diverse skeletons: generates motions from text captions across different rig types, including objects and characters. Published at SIGGRAPH Asia 2026, with training/inference code, the…

Early signalGenerative mediaPython+93 stars today, ≈ 158 by evening
5.2
MisakaZentai/world-execute-me-dsh-pv
The complete source of an unofficial fan PV for Mili's "world.execute(me);", where every frame is a pure function of song time. A DeepSeek Harness-style chat window is rendered as HTML and screenshotted with Playwright…

Early signalGenerative mediaPython+39 stars today, ≈ 68 by evening
5.2
debpalash/VoiceStudio
A fully local, open-source ElevenLabs alternative for voice cloning, voice design, video dubbing, dictation, transcription and audiobook creation on your own hardware, with no account or API key. Supports 16 TTS and 11…

SteadyGenerative mediaPython+403 stars today, ≈ 748 by evening
4.7
harry0703/MoneyPrinterTurbo
A Python tool that auto-generates HD short videos from a topic or keyword, writing the script and assembling footage, voiceover, subtitles and music. It ships with AI Agent, WebUI, API, CLI and one-click publishing to…

BreakoutGenerative mediaPython+193 stars today, ≈ 321 by evening