ringger/transcribe-critic
Multi-source transcript merging inspired by textual criticism — LLM adjudicates multiple Whisper, YouTube captions & external transcripts for higher quality. Includes speaker diarization and summarization.
This tool helps you create highly accurate written transcripts from video or audio recordings, especially for lectures, interviews, or presentations. It takes a video URL (like YouTube) or audio podcast link, along with any existing captions or transcripts, and produces a single, meticulously reviewed transcript. Content creators, researchers, journalists, or anyone needing precise text from spoken content would find this invaluable.
Available on PyPI.
Use this if you need the most accurate possible transcript from a recording, especially when multiple sources (like YouTube captions and automatic speech recognition) are available.
Not ideal if you only need a quick, basic transcript from a single source and speed is your top priority over absolute accuracy.
Stars
14
Forks
1
Language
Python
License
MIT
Category
Last pushed
Mar 09, 2026
Commits (30d)
0
Dependencies
7
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/ringger/transcribe-critic"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
m-bain/whisperX
WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)
tsmdt/whisply
💬 Fast, cross-platform CLI and GUI for batch transcription, translation, speaker annotation and...
jim60105/docker-whisperX
Dockerfile for WhisperX: Automatic Speech Recognition with Word-Level Timestamps and Speaker...
MahmoudAshraf97/whisper-diarization
Automatic Speech Recognition with Speaker Diarization based on OpenAI Whisper
linto-ai/linto-stt
An automatic speech recognition API