jianchang512/gemini-speech2srt

使用 Gemini AI 转写音视频为 SRT 字幕

34
/ 100
Emerging

Implements intelligent audio segmentation using VAD (Voice Activity Detection) to split media into chunks before sending each to Gemini AI, ensuring precise subtitle timing that avoids the axis drift occurring with full-file processing. Provides both a Windows GUI executable and cross-platform Python deployment, with configurable prompts and proxy support for regions where Gemini access is restricted.

No commits in the last 6 months.

No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 18 / 25

How are scores calculated?

Stars

54

Forks

13

Language

Python

License

Last pushed

Jan 11, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/jianchang512/gemini-speech2srt"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.