notepipe 0.1.0__py3-none-win_amd64.whl

notepipe-0.1.0.dist-info/METADATA

@@ -0,0 +1,394 @@
+Metadata-Version: 2.4
+Name: notepipe
+Version: 0.1.0
+Requires-Dist: notepipe-asr-llama ; extra == 'llama'
+Requires-Dist: notepipe-asr-meta ; extra == 'meta'
+Requires-Dist: notepipe-asr-openvino ; extra == 'openvino'
+Requires-Dist: notepipe-asr-speech-swift ; extra == 'speech-swift'
+Requires-Dist: notepipe-asr-xai ; extra == 'xai'
+Requires-Dist: notepipe-source-ytdlp ; extra == 'ytdlp'
+Provides-Extra: llama
+Provides-Extra: meta
+Provides-Extra: openvino
+Provides-Extra: speech-swift
+Provides-Extra: xai
+Provides-Extra: ytdlp
+License-File: LICENSE
+Summary: Extensible engine and CLI that turns video and audio into Markdown notes
+License-Expression: MIT
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown; charset=UTF-8; variant=GFM
+Project-URL: Homepage, https://github.com/3ae3ae/notepipe
+Project-URL: Issues, https://github.com/3ae3ae/notepipe/issues
+Project-URL: Repository, https://github.com/3ae3ae/notepipe
+
+<h1 align="center">
+  <picture>
+    <source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/3ae3ae/notepipe/main/docs/wordmark-dark.svg">
+    <img src="https://raw.githubusercontent.com/3ae3ae/notepipe/main/docs/wordmark-light.svg" alt="notepipe" width="360">
+  </picture>
+</h1>
+
+<p align="center">
+  <strong>Turn video and audio into Markdown notes.</strong><br>
+  The transcript in readable paragraphs, arranged around screenshots of what was on screen,<br>
+  optionally proofread, summarized or extended by the AI model of your choice.
+</p>
+
+<p align="center">
+  <a href="https://github.com/3ae3ae/notepipe/actions/workflows/ci.yml"><img alt="CI" src="https://github.com/3ae3ae/notepipe/actions/workflows/ci.yml/badge.svg"></a>
+  <a href="https://pypi.org/project/notepipe/"><img alt="PyPI" src="https://img.shields.io/pypi/v/notepipe"></a>
+  <a href="https://crates.io/crates/notepipe"><img alt="crates.io" src="https://img.shields.io/crates/v/notepipe"></a>
+  <a href="https://github.com/3ae3ae/notepipe/blob/main/LICENSE"><img alt="License: MIT" src="https://img.shields.io/badge/license-MIT-blue.svg"></a>
+</p>
+
+```sh
+notepipe lecture.mp4
+```
+
+```markdown
+---
+title: "Introduction to Compilers"
+source: "https://www.youtube.com/watch?v=…"
+author: "Example University"
+duration: "1:12:40"
+created: "2026-10-21T09:30:00Z"
+generator: "notepipe 0.1.0"
+---
+
+# Introduction to Compilers
+
+## Overview
+A compiler translates a program in stages, from characters to tokens, trees and finally machine code.
+
+## [03:12](https://www.youtube.com/watch?v=…&t=192s)
+
+![03:12](images/0002.jpg)
+
+The first stage is lexical analysis. The scanner reads characters and groups them into tokens such as identifiers,
+numbers and operators.
+```
+
+notepipe works on lectures, talks, meetings and podcasts. It is a dependable command-line tool on its own, and a
+component that other programs can build on.
+
+## Why notepipe
+
+- **Extensible without forking.** Websites, local speech engines and vendor APIs are *adapters*: small separate programs
+  with a documented contract, written in any language, installed as extras and attached with one line of configuration.
+  What the AI does is a prompt you write. A hook runs your own program after each note.
+- **Portable.** A single binary for Linux and macOS on x86_64 and arm64 and for Windows on x86_64, and it builds on
+  Android through Termux. Its only requirement is ffmpeg. Speech recognition and AI go through OpenAI-compatible APIs, so any provider, a server of your
+  own or a local engine will do; no account, vendor or model is built in.
+- **Reliable.** A note is built completely before it replaces the previous one, so a failed or interrupted run never
+  leaves a half-written or lost note. Finished work is cached: downloads, screenshots, transcripts and AI responses are
+  reused, and an interrupted transcription resumes where it stopped. Ctrl-C stops every process notepipe started. Every
+  code change is tested in CI on Linux, macOS and Windows.
+- **Plain, durable output.** Markdown, JPEG and JSON in an ordinary folder, readable by any editor, notes app or script.
+- **Private.** No telemetry. Audio and text go only to the services you configure, or nowhere at all with local
+  adapters.
+
+[docs/design.md](https://github.com/3ae3ae/notepipe/blob/main/docs/design.md) describes the design and the principles behind it.
+
+## Contents
+
+[Installation](#installation) · [Quick start](#quick-start) · [Configuration](#configuration) ·
+[Speech recognition](#speech-recognition) · [AI stages and prompts](#ai-stages-and-prompts) · [Adapters](#adapters) ·
+[The note](#the-note) · [Using notepipe from other programs](#using-notepipe-from-other-programs) ·
+[Acknowledgements](#acknowledgements)
+
+## Installation
+
+notepipe needs [ffmpeg](https://ffmpeg.org/download.html) on your `PATH` (`brew install ffmpeg`, `sudo apt install
+ffmpeg`, `winget install ffmpeg`, or `pkg install ffmpeg` in Termux).
+
+Install it with [uv](https://docs.astral.sh/uv/), choosing the extras for what you need:
+
+| You want notes from | Install |
+|---|---|
+| local video and audio files | `uv tool install notepipe` |
+| … and URLs (YouTube and the other sites yt-dlp supports) | `uv tool install "notepipe[ytdlp]"` |
+| … with local speech recognition through llama.cpp | `uv tool install "notepipe[llama]"` |
+| … with local speech recognition on an Intel NPU, CPU or GPU | `uv tool install "notepipe[openvino]"` |
+| … with local speech recognition on Apple silicon | `uv tool install "notepipe[speech-swift]"` |
+| … with xAI speech-to-text | `uv tool install "notepipe[xai]"` |
+| … with Meta speech-to-text | `uv tool install "notepipe[meta]"` |
+| any combination | `uv tool install "notepipe[ytdlp,llama]"` |
+
+Running `uv tool install` again replaces the installation, including its extras and `--with` packages, so list
+everything you want each time; `uv tool list --show-extras --show-with` shows the current set. pip and pipx accept the
+same extras.
+
+Other ways to install:
+
+- **Cargo:** `cargo install notepipe` installs the CLI; add adapters with pip or uv.
+- **Prebuilt binaries:** every [GitHub release](https://github.com/3ae3ae/notepipe/releases) has binaries and
+  checksums for Linux, macOS and Windows.
+- **Android:** in [Termux](https://termux.dev), run `pkg install rust ffmpeg python`, then `cargo install notepipe`;
+  add adapters with `pip install notepipe-source-ytdlp` and the like.
+
+| Platform | Architectures | Install with | Tested |
+|---|---|---|---|
+| Linux | x86_64, arm64 | uv, pip, pipx, Cargo, binary | in CI (x86_64) and containers (arm64) |
+| macOS | arm64, x86_64 | uv, pip, pipx, Cargo, binary | in CI (arm64) |
+| Windows | x86_64 | uv, pip, pipx, Cargo, binary | in CI |
+| Android (Termux) | arm64 | Cargo, pip | in a Termux container |
+
+## Quick start
+
+```sh
+notepipe lecture.mp4                       # writes ./<title>/note.md
+notepipe interview.m4a -o ~/notes          # audio works too; notes go under ~/notes
+notepipe talk.mp4 --subtitle talk.srt      # use a transcript you already have
+notepipe https://youtu.be/VIDEO_ID          # a URL, with notepipe[ytdlp]
+notepipe lecture.mp4 --stages summary      # add an AI summary at the top
+```
+
+Subtitles are used when they exist: `lecture.srt` or `lecture.vtt` next to the file, or those of the video at the URL.
+Otherwise speech is transcribed; the first run in a terminal asks which speech service to use and saves the answer.
+`notepipe doctor` checks your setup, and `notepipe --help` explains every option.
+
+## Configuration
+
+```sh
+notepipe config init    # create the configuration file, with every setting explained in comments
+notepipe config path    # print where it is
+notepipe config show    # show the settings in effect
+```
+
+The file is `~/.config/notepipe/config.toml`, or `%APPDATA%\notepipe\config.toml` on Windows (`$XDG_CONFIG_HOME/notepipe/`
+when that is set). Its sections follow the order in which a note is made, and every command-line option names the
+setting it overrides:
+
+```toml
+[output]
+dir = "~/notes"
+
+[transcript]
+language = "ko"                     # empty: detect
+
+[speech]                            # used when there are no subtitles
+base_url = "https://api.openai.com/v1"
+model = "gpt-4o-mini-transcribe"
+
+[screenshots]
+mode = "stable"                     # wait for animated slides to settle
+
+[ai]                                # shared by every AI stage
+base_url = "https://api.openai.com/v1"
+model = "gpt-5.6-luna"
+
+[[ai.stages]]                       # stages run in this order
+name = "proofread"
+
+[[ai.stages]]
+name = "summary"
+model = "gpt-5.6-terra"             # a stage can use its own model, service, key or prompt
+request = { reasoning_effort = "medium" }
+```
+
+API keys can stay out of the file: `NOTEPIPE_SPEECH_API_KEY` and `NOTEPIPE_AI_API_KEY` are used when it has none.
+[docs/configuration.md](https://github.com/3ae3ae/notepipe/blob/main/docs/configuration.md) lists every setting.
+
+## Speech recognition
+
+Speech is located on your machine, cut into short segments and sent to the service in `[speech]`.
+
+| Service | `[speech]` settings |
+|---|---|
+| OpenAI | `base_url = "https://api.openai.com/v1"`, `model = "gpt-4o-mini-transcribe"` |
+| Groq | `base_url = "https://api.groq.com/openai/v1"`, `model = "whisper-large-v3-turbo"` |
+| Mistral | `base_url = "https://api.mistral.ai/v1"`, `model = "voxtral-mini-latest"` |
+| Audio-capable chat models | `api = "chat"` with the provider's `base_url` and `model` |
+| Any OpenAI-compatible server you run | its `base_url` |
+| xAI, Meta | the [`xai`](#xai--xai-speech-to-text) or [`meta`](#meta--meta-speech-to-text) adapter |
+| llama.cpp, Intel NPU, Apple silicon (on your machine) | the [`llama`](#llama--llamacpp), [`openvino`](#openvino--intel-npu-cpu-or-gpu) or [`speech-swift`](#speech-swift--apple-silicon) adapter |
+
+## AI stages and prompts
+
+An AI stage sends the note to an OpenAI-compatible chat model with a prompt, and puts the answer back into the note.
+It reads either each paragraph or the whole transcript, and writes in place of each paragraph, below it, or at the top
+of the note. Stages run in the order you list them, each with its own model if you like.
+
+Two stages are built in: `proofread` corrects recognition errors and removes filler, and `summary` adds an overview, key
+points and a timed outline. **Every prompt is yours to change.** Give a built-in stage your own prompt:
+
+```toml
+[[ai.stages]]
+name = "summary"
+prompt = "Summarize this lecture for a student who missed it: the main argument, each new term with its definition, and what to review."
+```
+
+or write a stage of your own in a few lines:
+
+```toml
+[[ai.stages]]
+name = "translate"
+input = "paragraphs"                # each paragraph …
+output = "below"                    # … gets the model's answer underneath
+prompt = "Translate each item into Korean. Keep names, code and formulas unchanged."
+
+[[ai.stages]]
+name = "action-items"
+input = "transcript"                # the whole transcript …
+output = "top"                      # … and the answer at the top of the note
+prompt = "List the decisions and action items in this meeting as a Markdown checklist, with owners where named."
+```
+
+`--stages translate,summary` picks stages for one run, `--no-stages` skips them, and `--proofread-prompt` replaces the
+proofread prompt once. Any OpenAI-compatible chat service works, including OpenAI, Anthropic
+(`https://api.anthropic.com/v1`), Google Gemini (`https://generativelanguage.googleapis.com/v1beta/openai`), OpenRouter,
+Groq, and local servers such as Ollama (`http://localhost:11434/v1`) or LM Studio. Anything else, such as the OpenAI
+Responses API or access through a subscription, connects through an [AI adapter](https://github.com/3ae3ae/notepipe/blob/main/docs/adapters.md#ai-adapters).
+
+## Adapters
+
+Adapters connect notepipe to things it does not do itself: downloading from websites, and speech engines or AI services
+that are not OpenAI-compatible. Each is a separate package with a small program that notepipe starts when needed. The
+official adapters are extras of the `notepipe` package; install several at once with `uv tool install
+"notepipe[ytdlp,llama]"`.
+
+### `ytdlp` — URLs
+
+Downloads from YouTube and the other sites [yt-dlp](https://github.com/yt-dlp/yt-dlp) supports, with the video's
+subtitles and details. It honors your yt-dlp configuration and is used for URLs as soon as it is installed.
+
+```sh
+uv tool install "notepipe[ytdlp]"
+```
+
+### `llama` — llama.cpp
+
+Runs a speech model such as Qwen3-ASR with [llama.cpp](https://github.com/ggml-org/llama.cpp)'s `llama-server`, on a
+CPU or GPU. Requires `llama-server`.
+
+```sh
+uv tool install "notepipe[llama]"
+```
+
+```toml
+[speech]
+adapter = ["notepipe-asr-llama", "-hf", "ggml-org/Qwen3-ASR-1.7B-GGUF:Q8_0"]
+concurrency = 1
+```
+
+### `openvino` — Intel NPU, CPU or GPU
+
+Runs Qwen3-ASR or Whisper with [OpenVINO](https://github.com/openvinotoolkit/openvino.genai), on an Intel NPU by
+default.
+
+```sh
+uv tool install "notepipe[openvino]"
+```
+
+```toml
+[speech]
+adapter = ["notepipe-asr-openvino"]  # add "--device", "CPU" (or "GPU") to choose the device
+concurrency = 1
+```
+
+### `speech-swift` — Apple silicon
+
+Runs Qwen3-ASR on MLX, or Qwen3-ASR 0.6B and Whisper on Core ML, with
+[speech-swift](https://github.com/soniqo/speech-swift). macOS 15 or later on Apple silicon. Built in CI; not yet verified
+on hardware.
+
+```sh
+uv tool install "notepipe[speech-swift]"
+```
+
+```toml
+[speech]
+adapter = ["notepipe-asr-speech-swift"]
+concurrency = 1
+```
+
+### `xai` — xAI speech-to-text
+
+Connects notepipe to [xAI's speech-to-text API](https://docs.x.ai/developers/model-capabilities/audio/speech-to-text).
+
+```sh
+uv tool install "notepipe[xai]"
+```
+
+```toml
+[speech]
+adapter = ["notepipe-asr-xai"]
+model = "grok-voice-transcribe-2.0"  # the key comes from api_key or NOTEPIPE_SPEECH_API_KEY
+```
+
+### `meta` — Meta speech-to-text
+
+Connects notepipe to [Meta's speech-to-text API](https://dev.meta.ai/docs/speech-to-text).
+
+```sh
+uv tool install "notepipe[meta]"
+```
+
+```toml
+[speech]
+adapter = ["notepipe-asr-meta"]
+model = "muse-voice-transcribe-1.0"  # the key comes from api_key or NOTEPIPE_SPEECH_API_KEY
+```
+
+### Your own
+
+An adapter is any program that follows a short contract, so it can be written in any language; a complete example in
+Python takes a few dozen lines. [docs/adapters.md](https://github.com/3ae3ae/notepipe/blob/main/docs/adapters.md) describes all three kinds: speech, AI and download.
+Install one next to notepipe with `uv tool install notepipe --with <package>`, or put it on your `PATH`.
+
+## The note
+
+Each note is a folder named after the title:
+
+```
+Introduction to Compilers/
+├── note.md        Markdown with YAML front matter
+├── note.json      the same content as data
+└── images/        0001.jpg, 0002.jpg, …
+```
+
+A later run on the same recording replaces its folder; a different recording with the same title gets a `-2`, `-3`, …
+suffix, and a recording whose title has changed gets a folder for its new title. Each section's time links to the recording, at that moment where the source allows it.
+
+## Using notepipe from other programs
+
+The command line is notepipe's integration interface. Pass settings on standard input and read progress as JSON lines:
+
+```sh
+notepipe "$SOURCE" -o "$OUT" --config - --json < config.toml
+```
+
+[docs/cli.md](https://github.com/3ae3ae/notepipe/blob/main/docs/cli.md) documents the events, exit codes, `note.json`, caching, and the completion hook that runs your
+own program after each note is written.
+
+## Project status
+
+notepipe is young (0.x). The configuration format, the command-line interface and `note.json` may still change; every
+change is recorded in the [changelog](https://github.com/3ae3ae/notepipe/blob/main/CHANGELOG.md).
+
+## Contributing
+
+Issues and pull requests are welcome; [CONTRIBUTING.md](https://github.com/3ae3ae/notepipe/blob/main/CONTRIBUTING.md) explains how to build, test and propose a
+change. Please report security problems privately, as described in [SECURITY.md](https://github.com/3ae3ae/notepipe/blob/main/SECURITY.md).
+
+## Acknowledgements
+
+notepipe began as a fork of **[course2md](https://github.com/mizorewww/course2md)** by
+[mizorewww](https://github.com/mizorewww). course2md showed how useful slide-illustrated notes made from recordings can
+be, and notepipe still stands on its foundations: the screenshot detection, subtitle handling and timeline alignment at
+the heart of notepipe were adapted from it. Thank you to mizorewww and to everyone who
+[contributed to course2md](https://github.com/mizorewww/course2md/graphs/contributors). If you are looking for a desktop
+app with a notes library, course2md is the place to go.
+
+course2md's screenshot detection follows [yt-slide-mark](https://github.com/exopoiesis/yt-slide-mark) by exopoiesis.
+notepipe is also built on [FFmpeg](https://ffmpeg.org), [earshot](https://crates.io/crates/earshot) for speech
+detection, and, through its adapters, [yt-dlp](https://github.com/yt-dlp/yt-dlp),
+[llama.cpp](https://github.com/ggml-org/llama.cpp), [OpenVINO](https://github.com/openvinotoolkit/openvino.genai) and
+[speech-swift](https://github.com/soniqo/speech-swift).
+
+## License
+
+notepipe is released under the [MIT License](https://github.com/3ae3ae/notepipe/blob/main/LICENSE), which keeps course2md's copyright notice alongside notepipe's
+own.
+

notepipe-0.1.0.dist-info/RECORD

@@ -0,0 +1,6 @@
+notepipe-0.1.0.data/scripts/notepipe.exe,sha256=5LyjX5Z-wXqUHSUzQn5RkGO4ets4Efb8rhjphl-n6gk,7106048
+notepipe-0.1.0.dist-info/METADATA,sha256=ZerCJ0gsKcaRgqEgG1-W032g6bw8ze1wxj5bksVMgWQ,17748
+notepipe-0.1.0.dist-info/WHEEL,sha256=8Aej0W0a6Cz6apA3IzJrTnxLRVLAt-w0Oh8SA3Con_c,94
+notepipe-0.1.0.dist-info/licenses/LICENSE,sha256=UHbFQlIefs29aZ72RpcdxsA-tQBuihFGuSoHc1Ms24M,1114
+notepipe-0.1.0.dist-info/sboms/notepipe.cyclonedx.json,sha256=HOI3gTbyoHjP031Uoblfv8CcJwKH5Lt3tbi8YRQ38ok,183193
+notepipe-0.1.0.dist-info/RECORD,,

notepipe-0.1.0.dist-info/WHEEL

@@ -0,0 +1,4 @@
+Wheel-Version: 1.0
+Generator: maturin (1.15.0)
+Root-Is-Purelib: false
+Tag: py3-none-win_amd64

notepipe-0.1.0.dist-info/licenses/LICENSE

@@ -0,0 +1,22 @@
+MIT License
+
+Copyright (c) 2026 mizorewww
+Copyright (c) 2026 3ae3ae
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.