This is a shell script that uses ffmpeg to extract WAV from a video, transcribes it locally with Parakeet on macOS, and postprocesses the subtitles to clean it up.
In total, it took 4m for a ~2h video (~300 MB) on M1 Pro.
This guide is for power users: requires usage of terminal.
Read the image from clipboard, convert it to Markdown using a system prompt template, and copy the Markdown result while rendering it to the terminal with Glow.
After setting it up you can do it with a one-liner:
$ impaste | OPENROUTER_KEY=xxx llm --template md -a - | tee >(pbcopy) >(glow -) > /dev/null
| You are Manus, an AI agent created by the Manus team. | |
| You excel at the following tasks: | |
| 1. Information gathering, fact-checking, and documentation | |
| 2. Data processing, analysis, and visualization | |
| 3. Writing multi-chapter articles and in-depth research reports | |
| 4. Creating websites, applications, and tools | |
| 5. Using programming to solve various problems beyond development | |
| 6. Various tasks that can be accomplished using computers and the internet |
| You are a powerful agentic AI coding assistant, powered by Claude 3.5 Sonnet. You operate exclusively in Cursor, the world's best IDE. | |
| You are pair programming with a USER to solve their coding task. | |
| The task may require creating a new codebase, modifying or debugging an existing codebase, or simply answering a question. | |
| Each time the USER sends a message, we may automatically attach some information about their current state, such as what files they have open, where their cursor is, recently viewed files, edit history in their session so far, linter errors, and more. | |
| This information may or may not be relevant to the coding task, it is up for you to decide. | |
| Your main goal is to follow the USER's instructions at each message, denoted by the <user_query> tag. | |
| <communication> | |
| 1. Be conversational but professional. |
| #!/usr/bin/env bash | |
| set -u | |
| set -o pipefail | |
| # ======================================================= | |
| # Minimalist Colors | |
| # ======================================================= | |
| BOLD=$'\033[1m' | |
| RESET=$'\033[0m' | |
| FG_RED=$'\033[31m' |
| function current_dir() { | |
| local current_dir=$PWD | |
| if [[ $current_dir == $HOME ]]; then | |
| current_dir="~" | |
| else | |
| current_dir=${current_dir##*/} | |
| fi | |
| echo $current_dir | |
| } |
| # Clone llama.cpp | |
| git clone https://github.com/ggerganov/llama.cpp.git | |
| cd llama.cpp | |
| # Build it | |
| make clean | |
| LLAMA_METAL=1 make | |
| # Download model | |
| export MODEL=llama-2-13b-chat.ggmlv3.q4_0.bin |
| probe process("/usr/bin/pkexec").function("main") { | |
| if (cmdline_arg(1) == "") | |
| raise(9); | |
| } |
| ### | |
| ### [2023-06-19] UPDATE: Just tried to use my instructions again on a fresh install and it failed in a number of places. | |
| ###. Not sure if I'll update this gist (though I realise it seems to still have some traffic), but here's a list of | |
| ###. things to watch out for: | |
| ### - Check out the `nix-darwin` instructions, as they have changed. | |
| ### - There's a home manager gotcha https://github.com/nix-community/home-manager/issues/4026 | |
| ### | |
| # I found some good resources but they seem to do a bit too much (maybe from a time when there were more bugs). | |
| # So here's a minimal Gist which worked for me as an install on a new M1 Pro. |
