Descript MCP, live: edit video from inside Claude, ChatGPT, and Codex nitter.cf/i/broadcasts/1RJjpbejv…

Heard of MCP, but not sure where to start? Teddy and Sam walk you through the process of connecting the Descript MCP to your AI assistant. If you want to learn more, join us later today to see what you can do once you're connected (we'll send a recording to everyone who registers): bit.ly/3VcIkqf

Community Office Hours nitter.cf/i/broadcasts/1YxNrbqrm…

Underlord has more brainpower now. Paid users can check out Opus 5.5 in Descript.

The Hit Factory has hosted Beyoncé, Michael Jackson, and, this week, Descript CEO Laura Burkhauser. Our panel spent 45 minutes on what a podcast is actually worth. This morning, we cut the clip to two minutes in Descript. More from Podcast Movement next week.

Wondering what an MCP is? Many of us are, including the social media manager that wrote this post. MCP is the USB-C of AI: one standard that plugs in everywhere, instead of every app inventing its own cable. Plug in Descript and Claude or ChatGPT will import your raw footage, remove the filler words, run Studio Sound, and export. You never open the app. What an MCP actually is, in under three minutes.

Community Office Hours nitter.cf/i/broadcasts/1kKzDPqgL…

How HubSpot's Starter Story team repurposes one video into dozens nitter.cf/i/broadcasts/1vKpPNdzd…

That video you keep meaning to make? Give it a morning. Make Content, Not Excuses returns to Descript’s SF HQ on Oct 6th for #SFTechWeek. Write, record, edit, ship. With help from our team. Leave with a video ready to post. Join us: partiful.com/e/2DaT8iADDtBmu…

Community Office Hours nitter.cf/i/broadcasts/1pJdRDPWq…

You have one move in your process you've never explained to anyone. This week, teach it. Descript + @contra are running a challenge: teach one thing from your workflow, made in Descript. $5,000 for the best one. Enter here: bit.ly/46xwDg9

Most tools try to do the editor's entire job. HubSpot's Starter Story team built one that only does the repetitive part. Hub & Spoke, on Descript's API: one video → 55 clips → 1.35M+ views. Sept 9, we get into how. Register → bit.ly/3Ui5LOB

Everyone has one move in their workflow they never explain. The cut that lets an interview breathe. The thing you do to every thumbnail that nobody asks about and everybody notices. Next week, a reason to get it out. The best ones win with Descript and @contra.

New! Captions that earn their screen time. 18 new caption designs, now in Descript—sorted by theme, from clean and quiet to loud and fun. See them in action here, then add them to your video: bit.ly/45TWOxq

You could stop doing all five of these by hand by Friday (that's tomorrow): → sales call → sizzle reel → webinar → filler-word-free cut → one video → ten languages → blog post → video → raw footage → social clips Ask for it in Claude or ChatGPT. Descript does the rest, no window switching. Sign up at bit.ly/4gczctO

Community Office Hours nitter.cf/i/broadcasts/1YGNrbQdz…

Most AI labs build general-purpose generative models. We don't. We take hard, specific problems in the editing workflow and build models that solve them. We're hiring researchers to do more of it. Some of what we've worked on lately: - Fix a wrong word without re-recording it. We trained our own continuous neural audio codec and a tightly coupled flow-matching generator for zero-shot speech regeneration. - Audio-driven lip sync. When you edit audio, the speaker's lips stop matching the words. We trained a codec + flow-matching model that regenerates only the facial regions that need it, keeping identity, lighting, and temporal consistency intact. - Jump cut smoothing. Cut part of a video and you usually get an obvious visual jump. Our model synthesizes a physically plausible bridge between the remaining clips, so the edit reads as one continuous take. That's some of the recent work. What's next is the bigger swing: multimodal understanding and agentic video editing—models that watch, listen, reason about, and eventually edit long-form media on their own. That's the work we're hiring for. The team's research: descript.com/research Apply: job-boards.greenhouse.io/des…

You don't micromanage your video edits anymore. You just ask. Underlord does the heavy editing and sweats the details—like catching that B-roll was landscape in a portrait video, and reshaping it before you notice. Reach it from your assistant (Claude, ChatGPT) or build it into your own workflow. No timeline edits required. Sign up at bit.ly/4gczctO

Community Office Hours nitter.cf/i/broadcasts/1OxwbnmDP…

Community Office Hours nitter.cf/i/broadcasts/1YGNrbrPe…