Who this is for
Anyone whose to-dos arrive at the worst possible moment to type, and who wants them captured and ordered instead of scattered.
The moment this saves you
The tasks hit me when I can't type, in the car, mid-shower, walking in, and by the time I'm at a keyboard half of them are gone and I'm working off a vague feeling that I'm forgetting something.
See it work
Messy spoken thought in. A clean, structured artifact out.
Okay things I need to do. Call the dentist back, that's kind of urgent, they close at 5. Email the landlord about the leak. Pick up the dry cleaning, no rush. Oh and I need to send that invoice today, today is important. Reply to Marcus about the meeting time. And buy a birthday gift for Dad, his birthday's Saturday so that one's got a deadline. Oh and water the plants but that's whenever.
To-do, June 5, 2026
Today / urgent
- ☐ Send the invoice (today)
- ☐ Call the dentist back (they close at 5)
- ☐ Reply to Marcus about the meeting time
This week
- ☐ Email the landlord about the leak
- ☐ Buy a birthday gift for Dad (birthday Saturday)
Whenever
- ☐ Pick up the dry cleaning
- ☐ Water the plants
The workflow
Record a voice note
Hit the hotkey and talk, no formatting, no typing.
Tag it with this context
Contextli shapes your words into the structured output above.
Find it later
Everything's searchable and organised by context.
Pull it into Claude or ChatGPT
Bring your contexts straight into your AI tools with the Contextli MCP.
Your raw recording and transcription stay on your device, so you can always go back to the original.
The prompt behind this context
I'm going to rattle off my tasks out loud, in no order, maybe with duplicates. Turn them into a dated to-do checklist grouped by urgency under bold headings: **Today / urgent**, **This week**, and **Whenever**. Use markdown checkboxes (`- [ ] task`). Infer urgency from cues I give ("today", "urgent", a deadline, "no rush", "whenever"); if I give no cue, put it under This week. Merge obvious duplicates. Keep any deadline I mention in parentheses after the task. Don't invent tasks or deadlines I didn't say. Output only the checklist.
Make it your own. This is a starting point. Once it's in Contextli, tweak the instructions so the output comes out exactly how you like it.
Use this context
One click copies it and shows you exactly how to drop it into Contextli.
Next, open Contextli, go to the Contexts page, click Import, choose From JSON, paste, then Import Context. It is ready to use.
Make it your own. This is a starting point. Once it's in Contextli, tweak the instructions so the output comes out exactly how you like it.
Your raw recording and transcription stay on your device, so you can always go back to the original.
Related contexts
Brain Dump
Your head's too full to think, tasks, worries, ideas, all tangled. Just say everything out loud, in whatever messy order it comes. You get it back sorted into to-dos, ideas, and worries, so your brain can finally let go of holding it all.
Grocery List
You notice you're low on something with your hands full and forget it by the store. Say 'Hey Siri, dictate with Contextli' and rattle off what you need. You get a list grouped by aisle, so you stop wandering back for the milk you walked right past.
Weekly Review
Sunday rolls around and you mean to review the week, but staring at a template kills it. Just talk through what got done, what slipped, and what you learned. You get a structured weekly review you'll actually reread next Sunday.
Questions people ask
Questions knowledge workers ask about Voice To-Do List
How do I capture a to-do list by voice so it is actually organized?
Open Contextli, select the Voice To-Do List context, and speak your items in any order. The context groups related items, identifies priorities, and produces a task list you can paste into Slack, Notion, or email. You do not need to sort while speaking; say what comes to mind and let the context handle the structure.
What is the best way to capture tasks and ideas that come up during the day?
The habit that works is immediate capture with zero friction. The Voice To-Do List context lets you speak a to-do list in 10 to 20 seconds and produces a task list. You paste it into Slack, Notion, or email at the next natural pause. Because capturing is fast, you actually do it instead of telling yourself you will remember.
Can I build a to-do list by voice while doing other things?
Yes. With the Voice To-Do List context in Contextli, you can speak a to-do list while cooking, commuting, or doing anything else hands-free. The context formats your spoken list into a task list that is ready when you need it.
How do I avoid losing the things I mean to get to?
Capture them the second they surface. The Voice To-Do List context turns a quick spoken note into a task list in seconds, so nothing lives only in your head. You review and act on it later from Slack, Notion, or email, instead of trusting yourself to remember.
How do I add this context to Contextli?
Copy the context on this page, then open Contextli and go to the Contexts page. Click Import, choose From JSON, paste it into the Import from Clipboard window, and click Import Context. It is ready to use in under 30 seconds. If you do not have Contextli yet, you can download it for free first.
Is my voice recording private? Does Contextli send it anywhere?
Your voice recording and the transcription are stored on your device only. Contextli processes your audio locally and does not send your recordings or transcription text to any server. The structured output it produces is text you control, and you decide where it goes.
Can I change what the output looks like?
Yes. Every context in Contextli is a starting point you can edit. Open the context in the app, change the instructions to adjust the structure, tone, or fields, and save. The next time you use it, the output reflects your changes. You are not locked into the default format.
Do I need to install an app to use this context?
Yes. Contextli is a free app. Download it, then copy this context and paste it into the Import from Clipboard window on the Contexts page. The whole process takes about 30 seconds.