sh1nny0u

sh1nny0u / ASMR-J2C

Public

将日语（或其他语言）原音频转换为中文语音的本地工具。

42
2
100% credibility
Found May 12, 2026 at 42 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

A local web tool that replaces speech segments marked in Chinese LRC subtitles within original audio with Chinese TTS voices generated by IndexTTS2, while preserving background sounds and pauses.

How It Works

1
🔍 Discover ASMR dubbing tool

You find a simple local tool that turns Japanese ASMR audio into Chinese by swapping speech parts using subtitles.

2
📥 Download and setup

Download the folder and double-click the easy setup files to install everything needed, including the voice generator.

3
🚀 Launch the web page

Click start to open a friendly web interface in your browser, ready for your files.

4
📤 Upload your files

Drop in your original audio, Chinese subtitles file, and a short voice sample for the new speaker.

5
⚙️ Customize voice style

Tweak emotions or speed to match the original feel, then hit generate to start dubbing.

6
⏳ Watch it work

See the progress as it speaks each subtitle line, keeping whispers and sounds perfect.

🎉 Download your dubbed ASMR

Grab the new audio file with Chinese speech seamlessly blended in, ready to enjoy.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 42 to 42 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is ASMR-J2C?

ASMR-J2C is a Python tool for dubbing foreign-language ASMR audio—like Japanese clips—into Chinese speech using LRC subtitles. Upload the original audio, Chinese LRC file, and a reference voice sample; it swaps timed speaking segments with IndexTTS2-generated Chinese TTS while preserving background whispers, pauses, and ambiance. Output is a seamless WAV or MP3 with matched volume and duration.

Why is it gaining traction?

It runs fully local with one-click Windows batch setup, no cloud dependency, and taps IndexTTS2 for zero-shot TTS with emotion tweaks like sadness or surprise via sliders. Developers dig the web UI for previewing jobs, pausing/resuming long processes, and real-time progress—far smoother than scripting raw TTS pipelines. At 42 stars, it's niche but hooks ASMR enthusiasts needing precise, offline j2c dubbing.

Who should use this?

ASMR creators localizing Japanese roleplays to Chinese, podcasters dubbing foreign whispers, or hobbyists building multilingual binaural audio libraries. Ideal for Python users with decent GPUs handling TTS loads, especially those scripting custom emotion controls or batch-processing subtitle files.

Verdict

Try it for ASMR-j2c workflows if you have IndexTTS2 running—solid user experience despite 1.0% credibility from low stars and early-stage docs. Maturity lags on edge cases like noisy LRC, but it's a practical starter for local dubbing.

(178 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.