✍️ Transcribe and summarize YouTube videos using Whisper
- Go 58.3%
- HTML 15.6%
- CSS 10.3%
- Dockerfile 6.5%
- JavaScript 6.1%
- Other 3.2%
| .github/workflows | ||
| cmd | ||
| docs | ||
| internal | ||
| .dockerignore | ||
| .gitignore | ||
| AGENTS.md | ||
| docker-compose.yml | ||
| Dockerfile | ||
| go.mod | ||
| go.sum | ||
| LICENSE | ||
| main.go | ||
| pull_ollama_model.sh | ||
| README.md | ||
✍️ Transcribe YouTube videos using local AI models
Requirements
- Go >= 1.25
Features
- Transcribe YouTube audio using a local Whisper model
- Summarize the transcription using an OpenAI-compatible API
- Queue multiple video transcriptions
Usage
Program usage
USAGE:
yt-transcribe [global options] [command [command options]]
COMMANDS:
version Show current version
transcribe Transcribe a YouTube video
runserver Start HTTP server for YouTube transcription and queue management
help, h Shows a list of commands or help for one command
GLOBAL OPTIONS:
--help, -h show help
License
yt-transcribe is under the terms of the MIT License, following all clarifications stated in the license file.
