@@ -8,13 +8,13 @@ were often broken in a way that only showed up on somebody else's machine.
 
 ---
 
-## 0.1.2 — 2026-08-10
+## 0.1.2 (2026-08-10)
 
 ### Fixed
 
 - **Your clip settings are remembered again.** Turning captions off, closing
   the app and reopening it brought captions back on. Five settings behaved this
-  way — captions, 60s+ clips, podcast mode, longform and its mode. They were
+  way: captions, 60s+ clips, podcast mode, longform and its mode. They were
   read from storage on startup but never actually saved.
 - **The Watermark tickbox works.** It silently refused to stay ticked when no
   branding profile existed yet. It now explains that a profile has to be
@@ -25,24 +25,24 @@ were often broken in a way that only showed up on somebody else's machine.
 
 ### Changed
 
-- **The Models page makes sense.** It had one heading — "Your hardware" — over
+- **The Models page makes sense.** It had one heading, "Your hardware", over
   rows like "Multilingual" and "Newer Gemma", which are not hardware, and a
   "Why" column carrying licences and warnings at the same time. There are now
   two tables: what your machine can run, and what to pick for a particular job.
   `gemma3:4b` also appeared twice; it is one row now.
 - **More models to choose from**, all free to run locally and all usable on
   clips you earn from. `gemma4:e2b` and `gemma4:e4b` are built for ordinary
-  local machines and are recommended alongside the Gemma 3 line — `e2b` for a
+  local machines and are recommended alongside the Gemma 3 line. `e2b` suits a
   low-power or older PC, `e4b` anywhere `gemma3:4b` fits. Qwen3 for translation
   and multilingual work, and Mistral Nemo or Phi-4 for anyone who wants a
   plainly permissive licence.
 
 ---
 
-## 0.1.1 — 2026-08-09
+## 0.1.1 (2026-08-09)
 
 The release that made 0.1.0 usable. Both bugs were packaging mistakes, and both
-were invisible on a development machine — which is exactly how they reached a
+were invisible on a development machine, which is exactly how they reached a
 release.
 
 ### Fixed
@@ -54,12 +54,12 @@ release.
   inside the app, but the downloader looked for it on the system instead of
   being told where it lived, so it could not join YouTube's separate video and
   audio streams. Twitch and Kick were unaffected, because their recordings
-  arrive as a single stream — which is what made it look like a YouTube
+  arrive as a single stream, which is what made it look like a YouTube
   problem rather than a packaging one.
 
 ---
 
-## 0.1.0 — 2026-08-08
+## 0.1.0 (2026-08-08)
 
 First public alpha.
 
@@ -68,7 +68,7 @@ First public alpha.
 - Everything runs on your own computer. No uploads, no subscription, no cap on
   how many clips you make.
 - One installer. It carries the app, the engine, FFmpeg, the AI runtime and the
-  tracking and transcription models — the only thing fetched afterwards is the
+  tracking and transcription models. The only thing fetched afterwards is the
   language model, sized to your graphics card on first launch.
 - Editor for fixing anything the AI got wrong, multilingual captions, creator
   profiles that learn from your corrections, and a queue that runs unattended.
@@ -7,7 +7,7 @@ is in a release you can install today, not a plan.
 
 ## Now: Alpha
 
-The alpha is public. Its purpose is not to be perfect — it is to find out what
+The alpha is public. Its purpose is not to be perfect. It is to find out what
 breaks on machines that are not the developer's.
 
 **Shipped**
@@ -19,7 +19,7 @@ breaks on machines that are not the developer's.
 - Bug reports and feature requests: issue templates, plus an in-app Feedback
   Hub that needs no GitHub account
 - GitHub Discussions
-- Security scanning — CodeQL, Dependabot, secret scanning, a
+- Security scanning: CodeQL, Dependabot, secret scanning, a
   [security policy](SECURITY.md)
 - A container image for anyone who wants to work on the engine without
   installing PyTorch
@@ -52,7 +52,7 @@ AI improvements and performance work. Start with
 
 None of this delays the alpha.
 
-- **Gaming and split-screen**, done properly — the framing has to reliably find
+- **Gaming and split-screen**, done properly. The framing has to reliably find
   the action, and tracking has to tell a streamer from a character inside the
   game
 - **Reaction videos**, which need the app to understand the video being reacted
@@ -74,7 +74,7 @@ the app gets better as your hardware does rather than as someone's subscription
 tier does.
 
 Consumer AI hardware is improving quickly. The architecture is kept modular so
-newer models and faster hardware can be adopted without a redesign — as
+newer models and faster hardware can be adopted without a redesign. As
 machines like the NVIDIA RTX Spark and future AI-accelerated GPUs arrive, the
 same application should be able to run larger local models, infer faster,
 analyse video better and automate more.
 
@@ -83,7 +83,7 @@ <h1>Changelog</h1>
 
       <section>
         <div class="wrap">
-          <h2>0.1.2 &mdash; 10 August 2026</h2>
+          <h2>0.1.2 (10 August 2026)</h2>
           <ul class="ticks">
             <li>
               <strong>Your clip settings are remembered again.</strong> Turning captions off,
@@ -116,7 +116,7 @@ <h2>0.1.2 &mdash; 10 August 2026</h2>
 
       <section>
         <div class="wrap">
-          <h2>0.1.1 &mdash; 9 August 2026</h2>
+          <h2>0.1.1 (9 August 2026)</h2>
           <p class="section-lead">
             The release that made 0.1.0 usable. Both bugs were packaging mistakes, and both
             were invisible on a development machine, which is exactly how they reached a
@@ -132,7 +132,7 @@ <h2>0.1.1 &mdash; 9 August 2026</h2>
               <strong>YouTube downloads failed.</strong> FFmpeg ships inside the app, but the
               downloader looked for it on the system instead of being told where it lived, so
               it could not join YouTube's separate video and audio streams. Twitch and Kick
-              were unaffected, because their recordings arrive as a single stream &mdash;
+              were unaffected, because their recordings arrive as a single stream,
               which is what made it look like a YouTube problem rather than a packaging one.
             </li>
           </ul>
@@ -141,7 +141,7 @@ <h2>0.1.1 &mdash; 9 August 2026</h2>
 
       <section>
         <div class="wrap">
-          <h2>0.1.0 &mdash; 8 August 2026</h2>
+          <h2>0.1.0 (8 August 2026)</h2>
           <p class="section-lead">First public alpha.</p>
           <ul class="ticks">
             <li>
 
@@ -159,14 +159,14 @@ <h2>The long-term idea</h2>
           </p>
           <p class="section-lead">
             Consumer AI hardware is improving quickly. The architecture is kept modular so
-            newer models and faster machines can be adopted without a redesign — as hardware
+            newer models and faster machines can be adopted without a redesign. As hardware
             like the NVIDIA RTX Spark and future AI-accelerated GPUs arrives, the same
             application should run larger local models, infer faster, analyse video better
             and automate more.
           </p>
           <p class="note">
             The goal is an open-source creator platform that becomes more capable over time
-            because local AI hardware does — not one that becomes more expensive.
+            because local AI hardware does, not one that becomes more expensive.
           </p>
           <div class="cta-row">
             <a class="btn btn-accent" href="https://github.com/ColinGPT9/clips-studio/blob/main/ROADMAP.md" target="_blank" rel="noopener noreferrer">Full roadmap on GitHub</a>