Your best ideas die in Voice Memos. Mine land in GitHub about 20 seconds after I stop talking. No apps, no copy paste, no guilt.
I wired a tiny iOS Shortcut to do the grunt work. The bot is just the shovel. The outcome is the treasure: a clean, deduped GitHub issue with title, bullets, labels, and the transcript.
How it actually flows:
- Record a 30-60s voice memo.
- Share to my Shortcut called Voice → Git Issue.
- It transcribes in the cloud using a cheap model for speech to text - about a third of a cent per minute.
- A tiny format pass turns my ramble into JSON: title under 80 chars, 1-3 bullets, labels, assignee, optional due date.
- It reads inline tags I say out loud: label: bug, assign: me, repo: owner/repo, due: Friday.
- Quick dupe check by searching the first few words of the title. If it finds a match, I tap Open or Continue.
- Optional: commit the .m4a to attachments/YYYY-MM and link it.
- Create issue. Open URL. Done.
The issue body is readable on purpose:
- Summary bullets on top
- Details with my original words
- Metadata with source time, optional audio link, parsed tags
Real timings on normal Wi‑Fi:
- Upload and transcription: around 10 seconds
- Format: under a second
- Dupe search and create: under 2 seconds From end of recording to posted issue: roughly 10-25 seconds. Well under 2 minutes even if you count the talking.
The turn:
- Your audio goes to the cloud. If it’s sensitive, use an on-device Whisper app and feed the transcript to the same Shortcut.
- GitHub has no real issue-attachment API. I commit the file or just link it. If you truly need native uploads in the issue body, GitLab is cleaner.
- Labels must exist or GitHub complains. Create them once.
- Storing a token in Shortcuts is convenient and risky. Use a GitHub App relay if you’re strict.
Who is this for: solo devs and small teams who live on iOS and GitHub and hate overhead.
My take: if it isn’t in your tracker in 2 minutes, it doesn’t exist. Automate the capture and move on. 🎙️
Want the Shortcut and a 1-page quick start? Comment VOICE and I’ll share.