FrameWords
Turn Hours of Video into Instant Knowledge.
What it does
Stop rewatching hours of footage to find what matters. Drop any video or audio into FrameWords — interviews, depositions, lectures, meetings, podcasts — and get back: - A perfect searchable transcript with timestamp links - A deep analysis report with key insights and themes - An AI expert you can ask anything about your footage. What used to take 6-10 hours now takes 15 minutes. No installation. No technical setup. Just upload and go. Try the live demo on real footage — no signup needed.
Does the same job
all alternatives →
- LLLanguage Learning from YouTube content2025 · fluentsubs.com · ▲40
Hi! I'm living as an expat in France and I had a hard time following the news. So I've been working on Fluentsubs that turns YouTube content into a language learning experience. YouTube videos up to 20 minutes can be transcribed and listened to. At the same time I made it easy to lookup certain words and automatically add spaced repetition cards using the given context. This means that you can also rehearse with a real voice and not with AI dubs. This works especially well for the somewhat smaller languages that have a small track on Duolingo, and now are desperately looking for content…
- ORObiklip – read transcripts, find and create video segments quickly2023 · obiklip.com · ▲12
I'm a video editor, but not very professional. I mostly edit speech and podcast videos to highlight interesting parts and make short clips. I've found that the most time-consuming task is finding interesting segments in a full-length video. It usually takes me 2-3 hours of continuous listening just to find the 'timestamps' where the interesting points start and end. I'm referring to source videos that are 30 min to 1 hour long. Nowadays, getting transcriptions for videos is easy with AI. So, why not use that to find segments? Reading through a transcription is much quicker and easier than…
More work this month
the category →
The app store for voice native apps that lives in your notch
Work · 29d ago · voiceos.com
Launched alongside, May 2026
the whole month →
Parallel agents, diff reviewer, and multi-model comparisons
Dev tools · May 2026 · kilo.ai
- NW
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
- FM
Dev tools · May 2026 · github.com