matcha-video

https://matcha.video - In-browser "pre-editor" for cutting down a long sequence of repeated takes for talking-head content to just the stuff you want to keep. - Aligns cuts to the speaker's pose so they aren't cut-to mid-blink or mid-word

- Exports cuts to FCP and DaVinci so you can use your existing editing flow

- Transcript editor with retake grouping and word-level cuts

- Dysfluency detection ("um", "uh")

- Free, in-browser. Optional pay for faster / better server ASR

Currently in beta, free server ASR for new users. Please try it and give your honest feedback

https://matcha.video - In-browser "pre-editor" for cutting down a long sequence of repeated takes for talking-head content to just the stuff you want to keep.

- Aligns cuts to the speaker's pose so they aren't cut-to mid-blink or mid-word

- Exports cuts to FCP and DaVinci so you can use your existing editing flow

- Transcript editor with retake grouping and word-level cuts

- Dysfluency detection ("um", "uh")

- Free, in-browser. Optional pay for faster / better server ASR

Currently in beta, free server ASR for new users. Please try it and give your honest feedback

Similar to ground.news or thenewpaper.co ?

Same problem that got Obadiah Stane

Question for folks who work a lot with STT models - What is your favorite model that supports word-level timestamps, has good dysfluency detection (whisper isn't great), and is also supported by transformers.js?

Huggingface is just a git hosting service, like github. You can add up the sizes of all the files in the directory yourself

Also what's up with the knit dashboard?

Love this! Folks here should also check out https://wide.video if they're looking for a VERY full featured free in-browser video editor

It wasn't supposed to be literal :(

Just emailed you

That's a great question - these are sold as NFTs, and I think you only get the art, not the input parameters used to generate the art. I really like that idea though

Programmatic art is alive an well on the blockchain! One of my favorite artists in this space is Tyler Hobbs https://opensea.io/collection/fidenza-by-tyler-hobbs

Speech MCP Server - uses Kokoro TTS under the hood to give your LLM the ability to speak. I use it to have Cursor agents notify me when long running tasks are complete.

https://www.npmjs.com/package/speech-mcp-server

I've been working on a free, in-browser "pre" video editor. Upload your clip, use a transcript interface to cut it down to the takes and salient bits you want to keep, then export your cuts to FCP or Resolve to complete your editing. This tool saves me about 25-30% of my editing time.

Uses transformers.js & WebGPU for running transcription, so it's pretty fast. It's still a bit rough around the edges, so I'm looking for feedback.

https://matcha.video

seconded! I also enjoyed Zelda: Oracle of Ages / Seasons

I think this might be really cool, but when I tried clicking "playback actions" (unclear that this button means "play" and won't just take me to a list of actions) there was no sound.

Why do I need audio for a game about colors? I had to read the comments here to figure out why there was no score or indication of right / wrong

Okay I figured out why it wasn't loading on every tweet page. v0.3.6 is much more reliable now.

Dark mode is now supported as of v0.3.4 :) Thanks for your feedback

You're a true user! I just put up a small change that should improve reliability, let me address dark mode as well.

May I ask what you use the markdown for after its downloaded? Would you modify the output at all to make it better fit your use case?

Very cool! I'm very impressed that Twitter hasn't detected your selenium usage, it seems like they're really trying to push people towards their paid API.

I made a similar tool, except it's a browser extension that lets you download threads as markdown (then it's up to you to dump them into a DB or train a model on them or whatever), I'd love to get your feedback https://chromewebstore.google.com/detail/thread-to-markdown/... (firefox version also available)

Edit: Example output using tweet thread mentioned elsewhere in this post https://sharetext.io/c04b7c82

I'm not knowledgeable about networking - what's the benefit of having a 1gb lan and a 2.5gb wan? Why not have them both be the same?

Thread-to-Markdown, a browser extension for saving Twitter threads and articles to a markdown file.

---

Chrome https://chromewebstore.google.com/detail/eoapehkjjmekhkeinma...

Firefox https://addons.mozilla.org/en-US/firefox/addon/thread-to-mar...

---

Example output https://sharetext.io/?slug=61fa044c

Original thread https://x.com/johnrushx/status/1850899186528473097

I've been working on a free, in-browser "pre" video editor. Upload your clip, use a transcript interface to cut it down to the takes and salient bits you want to keep, then export your cuts to FCP or Resolve to complete your editing. This tool saves me about 25-30% of my editing time.

Uses transformers.js & WebGPU for running transcription, so it's pretty fast. It's still a bit rough around the edges, so I'm looking for feedback.

https://matcha.video