Record or import voice notes, then find, read, and replay them in a searchable journal. DictaWhisper transcribes on your computer, keeps the recording beside its transcript, and offers optional cleanup and suggested actions you can review.

Requires local setup, including Node and the selected transcription engine’s Python runtime. The exercised path is Windows with an NVIDIA GPU. Cleanup and search may use another host if you configure one.

Keep the thought without replaying the whole walk

Fictional recording and cleanup. Both versions belong to the same note; the audio remains available when you need to check what was said.

1 · Raw words The useful thought is inside the ramble

walk-note.webm → transcription

Um, for the garden, I think we should move the tomatoes to the south bed. Yeah, that’s the bit that gets sun in the afternoon.

2 · Saved note excerpt A readable version beside the recording

walk-note.json · selected fields

{
  "cleanedTranscription": "For the garden, I think we should move the tomatoes to the south bed. It gets sun in the afternoon.",
  "tags": ["garden", "tomatoes"]
}

The sidecar also keeps the raw transcript. Cleanup is optional.

3 · Revisit in the inbox Find the reason when you need it

Search for tomatoes, open the note, and read the thought: move them to the south bed for afternoon sun.

Play walk-note.webm to check the wording. Copy the audio and JSON together to keep the note with its source.

The recording becomes something you can find and reread.

Illustrative text, not a transcription-quality benchmark. If cleanup is unavailable, the raw transcript remains useful; check important details against the recording.

Read the note beside your library

Actual DictaWhisper Inbox: searchable library, selected transcript with timestamps, audio controls, and MayDos tab.
Actual DictaWhisper Inbox: searchable library, selected transcript with timestamps, audio controls, and MayDos tab.

The actual Inbox with fictional entries and synthetic transcript, timing, and action data. Select an entry to read it without leaving the library. The MayDos tab keeps possible actions alongside their source note. This capture shows the interface, not transcription or cleanup quality.

Package releases from 0.1.11 include compiled JavaScript and the inbox UI. Earlier npm releases do not start from an npm installation. Full prerequisites and setup are on Install.

What you get

  • Hit Record in the inbox, or drag an audio file onto the page. A phone folder that syncs in later (via Syncthing or any folder sync) is optional.
  • Copy the folder and you copied the journal. Open a note in any editor. There is nothing to export.
  • Speech is transcribed on this computer. A second pass can tidy the prose here, or on another computer you already use. If that computer is off or offline, you still have the raw words.
  • At home the inbox is a page on this machine. On Tailscale the same page works from your phone.
  • Readable paragraphs, a few tags, and playback that follows what you are reading.

A normal day

  1. Say something. Record in the inbox, or drop a file you already have.
  2. DictaWhisper writes the words, then a cleaner pass that drops the ums and adds tags.
  3. Open the inbox. Notes are grouped by month. The readable version is first; the raw speech is one click away.

If a phone app is also dropping files into a folder, those wait until the copy is finished. Browser recordings start right away.

Where the words get tidied

Transcription happens on your desktop. Tidying the prose can happen here too, or on another machine with a stronger writing model. ollanet is how DictaWhisper finds that helper.

The recording and its notes stay on this computer. Cleanup text goes only to the computer you name in ollanet.machine. Search indexing embeds note text on this computer, and uses another computer only if you set journal.embedHost. If this computer has no embedding model, search matches words only.

Where the files live

Browser recordings and drops go under watch.browserDropFolder (default ./data/audio-files). Optional phone folders are watch.roots. Each note is a pair:

data/audio-files/2026-09-10_walk-note.webm
data/audio-files/2026-09-10_walk-note.webm.json

The JSON holds raw transcription text (text, segments) and, when cleanup ran, cleanedTranscription and tags. The inbox Raw control shows the transcript. Sidecar downloads that file. A search index may also live at journal.index (default ./data/journal.sqlite). That index is not the journal. The pair is.

Sample names above are fictional.

If cleanup is down

The inbox still lists the recording. Status can read raw only, cleanup skipped, or cleanup failed. Retry queues another cleanup pass. pnpm retranscribe --reclean does the same from the terminal. Doctor warns when ollanet is unreachable. Transcription still requires the selected engine’s runtime; cleanup availability is a separate check.

Quick start

Read Install for hardware first. Then:

git clone https://github.com/Catalyst-Forge-LLC/dictawhisper.git
cd dictawhisper
cp config.example.json config.json
pnpm install
pnpm run doctor
pnpm dev

Ready signal: doctor exits 0, or only warnings remain. Then open http://localhost:7777. Flags live in the docs.

Built by Catalyst Forge LLC.