Public docs

SpeechToDo docs for the paid beta.

Start here for the current local-first voice workflow: where audio files go, what markdown artifacts are produced, and what is still intentionally early.

Start with setup Join the paid beta

Current setup shape.

SpeechToDo is early and founder-led. The paid beta is set up around a real folder workflow first, then tuned around how you already capture voice notes.

1

Choose a watched folder

Start with a local or synced workspace you control. The current beta is built around folder watching, not a closed notes dashboard.

2

Drop in audio files

Record with the tool you already use, then place audio files in the watched workspace. iCloud workflows are a first-class early path. Read the iCloud recorder guide for the default synced-folder setup.

3

Review markdown output

SpeechToDo turns the recording into editable transcript, summary, decisions, and tasks that can move into the rest of your system.

Artifact contract

What gets created.

The useful unit is not a raw transcript. It is a portable markdown artifact that keeps the source recording, transcript, summary, and follow-up work connected in your own workspace.

workspace/voice-note/action-doc.md 
# Product strategy voice note

## Source
- Audio: product-strategy.m4a
- Workspace: local synced folder

## Transcript
Raw voice capture, cleaned enough to review.

## Summary
- Core idea
- Important context
- Open questions

## Decisions
- Keep the artifact in markdown.

## Actions
- Review the transcript.
- Move tasks into the operating system.

Current product boundaries.

These docs should stay honest while the beta changes. SpeechToDo is useful when the file-native workflow matters more than a broad SaaS feature checklist.

Use SpeechToDo for

  • Voice notes, meeting recaps, and founder task dumps.
  • Local-first or synced-folder workspace workflows.
  • Markdown transcripts, summaries, decisions, and tasks.
  • Founder-supported paid beta setup and workflow tuning.

Use another tool for

  • A mature calendar meeting bot for every call.
  • Enterprise admin controls and team dashboards today.
  • Claims of fully offline AI processing before it is shipped.
  • Generic bulk transcription without a file workflow.

For the privacy posture behind these boundaries, read the local-first transcription page and the privacy policy.

Read next.

These pages explain the core local-first voice artifact pillar from different workflow angles.

Workflow hub

A routed overview of the markdown, task, iCloud, and local-first workflow pages.

Open workflow hub

Voice notes to markdown

The core workflow page for turning messy audio into editable markdown artifacts.

Open workflow page

iCloud recorder workflow

A practical folder-watching path for people who already capture voice notes through Apple devices.

Open iCloud guide

Local-first transcription

The ownership and boundary page for the local-first SpeechToDo positioning.

Open local-first page

Voice notes to tasks

How SpeechToDo turns rambling voice capture into reviewed actions and decisions.

Open task workflow

Support during the paid beta

Beta customers get direct founder support for setup and workflow tuning. Email hello@speechtodo.com when the docs leave a gap.