AICHE +Substack Integration

Voice input for newsletters

Speak your newsletter directly into Substack.

Download AICHE
Works on:
macOSWindowsLinux

The short answer: open the Substack editor, click into any text section, press ⌃+⌥+R (Mac) or Ctrl+Alt+R (Windows/Linux), speak for 45-60 seconds, and AICHE inserts the transcribed newsletter content at your cursor position.

Substack writers live and die by consistency. Your subscribers expect a newsletter on the schedule you promised, whether that is weekly, bi-weekly, or daily. The number one reason newsletters die is not lack of ideas. It is the gap between having something to say and getting it written down. You know what your next issue should cover. You have been thinking about it all week. But sitting down to type 1,200 words on Tuesday evening after a full workday feels like a second job. Voice dictation at roughly 150 words per minute means a 1,500-word newsletter draft takes about 10 minutes of speaking. That same draft takes 40-50 minutes to type. The math alone explains why this works, but the quality difference matters too. Spoken first drafts tend to sound more conversational, which is exactly the tone that performs best in email newsletters.

  1. Open Substack and click "New post" from your dashboard.
  2. Add your headline and subtitle in the title fields.
  3. Click into the body of the editor where you want to start writing.
  4. Press ⌃+⌥+R on Mac or Ctrl+Alt+R on Windows/Linux to start recording.
  5. Speak your newsletter content in sections. Start with the opening hook or story, then move into the main argument or insight.
  6. Press the hotkey again to stop. AICHE transcribes and inserts the formatted text.
  7. Repeat for each section of the newsletter. Add headings, images, links, or embeds using Substack's toolbar between dictation passes.

First drafts that sound like you

Newsletter readers subscribe to a person, not a publication. The voice in your writing is the product. When you type, there is a tendency to over-edit as you go, smoothing out the personality in favor of "correct" writing. You delete the aside that made the paragraph interesting. You rephrase the blunt sentence into something safer.

When you speak, the unfiltered version comes out first. Your natural cadence, your specific word choices, the way you actually explain things to people. AICHE captures that and Message Ready cleans up the punctuation and paragraph structure without flattening the personality. The result is a first draft that sounds like your speaking voice, which is usually the voice your subscribers signed up for. You still edit after dictating, but the editing is additive (inserting links, refining transitions) rather than trying to inject personality into sterile typed prose.

Substack Notes and short-form content

Substack Notes is the platform's short-form feed, similar to X posts but for your subscriber community. Notes require a different energy than full newsletters. They are quick thoughts, observations, questions, and links with brief commentary. Typing Notes feels like a distraction from the "real work" of writing the newsletter, so many Substack writers underuse the feature.

Voice makes Notes effortless. See something worth sharing, open Notes, press the hotkey, and speak your take in 15 seconds. You are done. Do this 2-3 times per day between newsletter issues and you keep your subscriber community engaged without taking meaningful time away from long-form writing. Notes also serve as idea incubation. Dictate a quick observation today, and next week it might become the seed of a full newsletter issue.

Subscriber replies and community threads

Substack's comment sections and discussion threads are where writers build real relationships with paying subscribers. But responding thoughtfully to comments takes time, and most writers either reply with one-liners or skip comments entirely. Neither approach builds the community that sustains a paid newsletter.

Voice lets you respond at the depth your subscribers deserve. Click into a reply field, press the hotkey, and speak a genuine, detailed response in 20-30 seconds. You can reference specific points from their comment, share additional context, or ask follow-up questions. When you have 15-20 comments on a post, working through them by voice takes 10 minutes. Typing the same quality of responses would take 30-40 minutes. That difference determines whether you actually engage with your community or just intend to.

Heads-up: Substack's editor auto-saves frequently. Dictate one section at a time, pause to let the editor save, then continue to the next section. This prevents losing content if your browser has issues. Also, dictate body text first and add formatting (headings, bold, block quotes) afterward. Separating content creation from structure keeps you in flow.

The pro-tip: enable Message Ready in AICHE settings for newsletter writing. Your conversational speech gets formatted into readable paragraphs with proper sentence structure that feels natural in an email context. The paragraphs land at the right length for email readability, typically 2-4 sentences each, because that mirrors how people naturally pause between thoughts while speaking.

Result: a 1,200-word newsletter that takes 70 minutes of typing becomes 10 minutes of dictation plus 15 minutes of editing and formatting. You publish on schedule consistently, your voice sounds more natural, and you actually have time to engage with subscribers in the comments.

Do this now: open a new Substack draft, press your hotkey, and dictate the opening story or hook for your next newsletter issue. Speak for 60 seconds without stopping to edit. See how much usable content lands on the page.

#documents#productivity