← All languages

Dutch Text to Speech: Free, In-Browser, Nothing Uploaded

Dutch has both neural tiers and a working step-down, which puts it in the best-supported group here — a group with only five members. Paste Dutch text, press play, and the audio is generated on your own device — no account, no upload, no character limit. This page is the honest version: which engines really speak Dutch (Nederlands), which ones silently do not, and what each one costs you.

Which engines actually speak Dutch

Quick TTS ships four TTS engines and lets you switch between them from one dropdown — but not all four cover every language, and the gaps are not the ones you would guess from the marketing.

EngineDutch?What that means
Web Speech APIYesYour operating system's built-in Dutch voices. No download, works on every device including iPhone and Android.
Piper (WebAssembly)YesVoice nl_NL-mls-medium. Runs without a GPU after a one-time model download.
Kokoro-82M (WebGPU)NoEnglish only. Hidden on every other language, because a voice you cannot select is not an option.
Supertonic HD (WebGPU)Yes44.1kHz studio-grade Dutch, one of fifteen mapped languages. WebGPU-only, ~380MB cached once.

Dutch is in the small set of languages where every tier of this product actually works:

One thing to set expectations on: the voices here are Netherlands Dutch. There is no Flemish (Belgian Dutch) model in the upstream Piper catalogue, and Supertonic maps Dutch as a single language rather than by region. Flemish text will be read correctly but with a Netherlands accent — worth knowing before you judge the output, given that Belgium is consistently among this site's larger markets.

The honest limits

Dutch is one of only five languages in this build with a working smaller Piper model — English, Spanish, Polish, Dutch and Arabic. If a device cannot allocate nl_NL-mls-medium, Dutch steps down to nl_NL-mls_5809-low — a step-down model the engine picks by itself, never in the voice dropdown — instead of falling back to the system voice, and devices reporting 4GB of RAM or less start on the smaller model rather than downloading the larger one and failing on it. Most languages here have no working step-down at all, because the smaller upstream models fail at inference in this runtime.

Supertonic HD needs WebGPU with no WebAssembly fallback and a one-time ~380MB cached download. The Web Speech API tier is strong for Dutch specifically — Windows, macOS and iOS all ship a competent Dutch voice — so the realistic question here is less "is there anything that speaks Dutch" and more "is the neural quality worth the download", which is a better problem to have than the one Arabic or Hindi readers face.

Nothing you paste is uploaded

This is the part that separates in-browser TTS from the cloud tools that look identical in a browser tab. A cloud tool sends your Dutch text to a server, synthesizes it there, and sends audio back — the page is a remote control. Quick TTS ships the engine to you instead and runs it on your CPU or GPU, so your text is never received by anyone. The test is simple: once the page and its model have loaded, the neural engines keep working with your network disconnected.

That matters most for the documents people actually want read aloud — a contract, a medical letter, coursework, an unpublished draft. It also means there is no "we phonemize non-English text on our server" asterisk, which is not true of every tool advertising local synthesis.

Reading Dutch documents, not just pasted text

PDF, DOCX, EPUB, ODT, RTF, HTML, TXT and Markdown are all parsed in the browser, so a whole Dutch EPUB or a long PDF opens and plays without a byte leaving your machine. A scanned PDF — a photo of text with no text layer — is handled by running OCR locally in WebAssembly rather than uploading the scan, which is precisely the case where local processing is worth the most.

Speed, volume and voice can all be changed mid-read and the current passage replays under the new settings without starting over. Switching the engine itself stops playback, so you press play once to start the new one — there is no mid-read handover of the remaining text between engines.

Frequently asked questions

Is Dutch text-to-speech free?

Yes. Quick TTS reads Dutch with no account, no character limit and no watermark. Synthesis runs in your browser on your own device, so there is no per-character server cost to meter and nothing to gate behind a sign-up.

Is my Dutch text uploaded anywhere?

No. The speech engine ships to your browser and runs locally, so the text you paste is turned into audio on your machine and never sent to a server. That is an architectural property, not a promise in a privacy policy — there is no server in the loop once the page has loaded.

What is the best Dutch TTS voice in the browser?

Supertonic HD is the highest-quality Dutch voice available here — 44.1kHz, running on WebGPU. If your machine has no usable GPU, Piper is the neural option that still runs. To get Dutch voices rather than English ones, open the app at quick-tts.com/nl/ — the neural voice list follows the page language.

Does it work on a phone?

The Web Speech API engine works on every modern phone with no download, and it is the default so the first play click always works. The neural engines are more demanding: Supertonic HD needs WebGPU and is effectively a desktop feature, and Piper runs more widely but can be slow on low-end hardware.

Can I download the Dutch audio?

Yes, as WAV or MP3, generated on your device. Anything longer than about 20,000 characters is packaged as a ZIP of audio parts so memory stays bounded on long documents.

Try it in Dutch — open the Nederlands app, not the English one

This is the one piece of setup worth knowing, because it is not obvious: the neural voice list follows the language of the page you are on. On the English homepage the Piper voices are the English ones, and Supertonic reads with the English language tag — so Dutch text pasted there will be pronounced as though it were English. Open the Nederlands version instead and the engine picks up Dutch voices, including nl_NL-mls-medium, automatically.

The one exception is Supertonic's "Auto language" toggle, which switches generation to a language-agnostic mode that reads mixed-language text with the right pronunciation per language without tagging anything by hand. That works from any page — it is the right choice for a document that is part Dutch and part English.

Written in Nederlands

These are the Dutch-language write-ups on this site. They are authored in Nederlands rather than translated from the English, so they are the better read if Nederlands is the language you would rather be reading in:

Each of this language's Piper voices also has a page of its own, covering the quality tier, what happens when your device cannot load the model, and how it compares to the HD option: nl_NL-mls-medium.

For the architecture behind all of this, see how in-browser text-to-speech works; for a tool-by-tool comparison with the other local TTS sites, see the comparison page.