OpenBrief – Local-first video downloader/summarizer
OpenBrief is basically a GUI for yt-dlp with some AI on top — paste a link, it downloads locally, and transcription and voice generation run with local AI on your machine. Summaries and chat over the transcript use an LLM, which is bring-your-own-key for now. It's open source and free.
OpenBrief – Local-first video downloader/summarizer launched on May 25, 2026 with 93 votes, #361 of 20,538 launches that month and more than 95% of that year's launches.
In plain words
OpenBrief is a desktop application that downloads videos from links and processes them locally on your machine. It transcribes audio using local AI and generates summaries through an LLM (which requires your own API key). Users can chat with transcripts and generate voice output, all while keeping their data on their computer. The tool is open source, free, and built as an interface around yt-dlp with integrated AI capabilities.
written from the facts on this page · September 2026
From the sources
Contribute to tantara/openbrief development by creating an account on GitHub.
Import a video or audio file, extract its transcript, generate a grounded summary, and chat with the content — all on your desktop. OpenBrief is a pnpm/Turborepo workspace centered on a Tauri v2 desktop app. It supports importing local media or video URLs, downloading media through bundled tools, transcribing audio, generating grounded summaries, chatting with media context, organizing playlists, and exporting reusable notes. Build a searchable library from video links or local files, then extract transcripts and keep everything in one place. Open any item to read the transcript, generate a grounded summary, and chat with the media context side by side. client/ apps/ tauri/ Main OpenBrief…from github.com
Does a similar job
all alternatives →
- OOOWhisper – Ollama for realtime speech-to-text2025 · docs.hyprnote.com · ▲289
Hello everyone. This is Yujong from the Hyprnote team (https://github.com/fastrepl/hyprnote). We built OWhisper for 2 reasons: (Also outlined in https://docs.hyprnote.com/owhisper/what-is-this) (1). While working with on-device, realtime speech-to-text, we found there isn't tooling that exists to download / run the model in a practical way. (2). Also, we got frequent requests to provide a way to plug in custom STT endpoints to the Hyprnote desktop app, just like doing it with OpenAI-compatible LLM endpoints. The (2) part is still kind of WIP, but…
MacWhisper2023 · goodsnooze.gumroad.com · ▲123High quality text transcription with OpenAI's whisper on Mac
AI Video Transcriber (open source)2025 · github.com · ▲9Open‑source AI tool for multi‑platform video transcription
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 21d ago · stillwet.art
FastRouter.ai▲364Route requests to the right LLM for cost, latency & quality
AI · 23d ago · fastrouter.ai
Source: Show HN post ↗
Launched alongside, May 2026
the whole month →
Parallel agents, diff reviewer, and multi-model comparisons
Dev tools · May 2026 · kilo.ai
Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…
Life & fun · May 2026 · github.com
🌱 Private, quiet space for thinking. Simple app for .md files. - zakirullin/files.md
Dev tools · May 2026 · github.com