GUIDE

Notion text to speech: an audio version of any page

Notion is where many teams and students keep notes, wikis and plans, and there are good reasons to listen to them: review a lesson on the way to class, go through meeting notes while walking, or give a team an audio version of an onboarding page. Notion does not have a read-aloud button of its own.

SuperClonica gives you natural voices in 31 languages, free to try online, and a free engine that turns an exported page into an MP3 on your computer. Notion plays uploaded audio right on the page, so the voice ends up next to the text.

Browse voices Install the SuperClonica engine

What Notion can and cannot do

The engine drops Markdown marks such as # and ** while reading, so the exported page needs little cleanup.

  • Notion has no read-aloud of its own; browser extensions and screen readers can read pages with your system voice.
  • Notion can export a page as Markdown, plain text you can voice directly.
  • Notion’s audio block plays MP3, WAV and OGG files you upload.
  • On the Free plan each uploaded file must be under 5 MB, which is about five minutes of MP3 at 128 kbps.

Pick a voice free online

On the page of any voice, paste a sentence from your Notion page, 30 to 100 characters, choose the language and press Voice it. Listen to a few voices and keep the one your team or class will hear on every page.

Turn a page into an MP3

Digits are read as plain numbers, so write dates and versions the way they should sound.

  • Export the page as Markdown from its menu and unzip the download.
  • Install the free engine: python -m pip install superclonica-cpu.
  • Voice the page: superclonica --text-file page.md --voice F2 --lang en --normalize --output page.mp3.
  • Delete web addresses first: they are read in pieces.

Put the audio back on the page

Add an audio block at the top of the page and upload the MP3. If you are on the Free plan and the page is long, split the text into parts of about five minutes and voice each into its own file, or upload a shorter summary. The engine runs offline with no character limit, so private notes never leave your computer.

Voices for team pages

For pages your team or students hear, use the ten stock voices of the model, M1 to M5 and F1 to F5, free under the OpenRAIL-M license, or your own voice trained in the SuperClonica studio. Fan-made character voices from the catalog are for fan projects, not for work pages. Say on the page that the audio is made with AI.