jianchang512/speech2text-df

基于Dolphin模型的东方语言音视频转字幕api及webui

22
/ 100
Experimental

This tool helps content creators, educators, or anyone working with audio and video content to quickly generate accurate subtitles for Eastern languages and various Chinese dialects. You simply provide an audio or video file (like MP3 or MP4), and it outputs a subtitle file in formats like SRT, JSON, or plain text. It's designed for individuals who need to transcribe spoken content into written text for accessibility, translation, or content indexing.

No commits in the last 6 months.

Use this if you need to generate subtitles for audio or video files, especially those containing Chinese dialects or other Eastern languages, and require the output in common subtitle formats.

Not ideal if your primary need is for real-time transcription, or if you only work with Western languages not supported by this tool.

subtitle-generation video-production audio-transcription localization education
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

18

Forks

Language

HTML

License

MIT

Last pushed

Apr 03, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/jianchang512/speech2text-df"

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