About Whisperly

Whisperly is a free AI voice generator that turns written text into natural-sounding AI voices — and it does the whole job inside your browser. No account to create, no sign-up, no API key to paste, nothing to install. Paste your text, pick a voice, and press Convert. The audio is generated on your own device, and it's yours to download as an MP3.

Text to speech that runs on your device, not in the cloud

Most text-to-speech tools send your words to a cloud service and stream the audio back. Whisperly flips that around. It runs a neural AI TTS engine — sherpa-onnx, compiled to WebAssembly — directly on your computer's CPU, inside the browser tab. A voice model downloads once the first time you use it; after that, every conversion happens locally, with no round trip to a server.

Your words stay private

Because the synthesis runs on your device, your text and the audio it produces never leave it. Nothing is uploaded, logged or stored on a server — there isn't a backend that could read your content if it wanted to. Draft scripts, private notes, unpublished writing: convert anything you'd rather not hand to a third party.

Free, with no limits

On-device synthesis costs nothing per character, so Whisperly is free — no sign-up, no quotas, no rate limits, no upsell. Convert a single sentence or a 10,000-word article. The only real limit is your own hardware, and you can pause and resume long runs whenever you need to.

Dozens of AI voices and languages

Whisperly ships the multilingual Kokoro model — dozens of AI voices spanning English, Chinese, German, Spanish, French, Italian, Portuguese, Japanese and Hindi — plus dedicated Piper voices like Amy (US English) and Thorsten (German). Adjust the speaking speed to taste and download the result as an MP3.

Works offline, installs like an app

Once a voice model has downloaded, Whisperly caches it in your browser (IndexedDB), so you can keep converting text to speech with no connection at all. It installs as a progressive web app, too — opening straight into the editor alongside your other apps.

How it works

1. 1

   Paste your text. Type or paste anything you want spoken.

2. 2

   Pick a voice. Choose a language and voice, and set the speed.

3. 3

   Press Convert. The audio is generated on your device — play it back or download the MP3.