Workflow hub

Voice notes to markdown workflows, mapped by job.

SpeechToDo is built around a small set of file-native workflows: turn messy audio into markdown, review tasks before acting, keep synced-folder setup clear, and understand the local-first boundary.

Start with Cloud Choose a workflow ↓
workspace/voice-workflows.md 
# Voice workflow map

## Source
- Raw audio or synced recording

## Outputs
- transcript.md
- summary.md
- actions.md

## Review path
- Check source audio
- Edit markdown
- Move only reviewed work forward

Start with the job you need done.

Each page explains one angle of the same core wedge: user-owned voice artifacts instead of trapped transcripts or another dashboard.

Convert audio into markdown

Start here when the main problem is getting a voice memo, walking note, or audio file into an editable markdown workspace.

Open the markdown workflow

Turn voice dumps into tasks

Use this path when the recording contains decisions, follow-ups, open questions, and candidate tasks that need review.

Open the task workflow

Use an iCloud-backed folder

Choose this path when recordings already move from phone to Mac through iCloud Drive or another synced folder.

Open the iCloud guide

Check local-first boundaries

Review what lives in your workspace, where hosted processing may still apply, and which promises the beta does not make yet.

Open the boundary page

The shared artifact contract.

The pages differ by entry point, but the output shape should stay consistent enough to trust and reuse.

1

Source stays visible

Keep the recording filename and workspace context attached so the generated artifact can be checked against the original audio.

2

Markdown stays editable

Transcript, summary, decisions, and tasks should be plain files you can correct, link, copy, archive, or delete.

3

Actions stay reviewable

SpeechToDo should surface candidate work, then let you decide what moves into docs, issues, reminders, or daily review.

Use the files in your markdown vault.

If your operating system already lives in Obsidian, a notes folder, or a repo, the important promise is portability: SpeechToDo should produce markdown you can move there, inspect, and edit.

Good vault handoff

  • Keep the source recording filename beside the generated files.
  • Store transcript, summary, and actions as separate markdown artifacts.
  • Move reviewed notes into your vault when they are ready.
  • Use links, tags, or folders from your own system after review.

Current boundary

  • This is a portable markdown workflow, not a dedicated Obsidian plugin.
  • SpeechToDo should not silently promote unreviewed voice output into trusted notes.
  • Automation to Drive, webhooks, or other systems should wait for explicit product support.
  • The vault remains yours; SpeechToDo only prepares files for reuse.

Compare by workflow, not by feature checklist.

Meeting assistants and transcription dashboards can be the right tools. SpeechToDo is narrower: file-native voice artifacts for operators who want the workspace to remain the source of truth.

SpeechToDo is a fit when

  • You want markdown files beside source recordings.
  • You use voice notes for founder decisions, tasks, or setup notes.
  • You want optional hosted intelligence without giving up file ownership.
  • You value clear beta boundaries over broad tool claims.

Another tool is a fit when

  • You need a mature calendar bot for every team meeting.
  • You want a shared cloud transcript dashboard as the main surface.
  • You need enterprise administration, permissions, and team analytics today.
  • You need a fully offline AI stack before it is shipped and documented.
Browse comparison routes Read public docs Review privacy policy

Try the desktop alpha
with your own recordings.

Download the early Mac or Windows build, point it at a workspace you control, and turn recordings into markdown transcripts, summaries, and action docs.

Download for Mac →
All options
Mac Notarized DMG for macOS Notarized Windows Unsigned portable ZIP for Windows x64 Unsigned alpha
Alpha release SpeechToDo Alpha
  • Mac notarized build and unsigned Windows ZIP
  • Local workspace and markdown outputs
  • Feedback shapes the paid beta
Cloud plans

Choose a tier inside the desktop Account panel.

Create or sign in to a SpeechToDo account in the app, then pick the Cloud tier that matches your monthly recording volume. Checkout opens with your account attached.

Student $6/mo 20 hours of hosted AI Pro Recommended $16/mo 60 hours for solo operators Business $30/mo 120 hours of hosted AI

Cloud checkout opens from the desktop app so your subscription attaches to the right account.

Markdown iCloud Gemini Obsidian Drive Notion soon MCP soon CLI Markdown iCloud Gemini Obsidian Drive Notion soon MCP soon CLI