unlimitedtts
How it works

Press Enter or Space to start voice dictation. Your browser may ask for microphone permission.

Import PDF, Word (.docx), ODT, EPUB, RTF, Markdown, HTML or text files. Files are read on this device and never uploaded.

Quick uses your device voices and starts immediately. Quality varies by device.

Check the language above. Choose it manually to override detection.

Import voice file

Supertonic powers Natural voices. Voice Builder was a custom voice service and has closed. Import an existing Supertonic 3 JSON backup; no audio upload is needed.

Supertonic migration guide

Choose the separately labeled Supertonic 3 JSON, up to 2 MB.

The voice tensors and name stay on this device. Keep an independent backup because clearing site data can remove local voices.

Drag to move through the text. Natural audio can be scrubbed after generation.

Import voice file

Voice Builder has closed. Import an existing Supertonic 3 backup to keep using it here.

Supertonic migration guide

Dictating a lot?

A dedicated USB microphone picks up far less room noise than a built-in laptop mic, so dictation needs fewer corrections.

Affiliate link — we may earn a commission at no cost to you.

Need to listen in private?

Noise-cancelling headphones keep playback to yourself on a train, in a shared office, or next to someone who is asleep — and quieten the room around you while you listen.

Affiliate link — we may earn a commission at no cost to you.

Want something ready offline?

Audible downloads too — thousands of human-narrated titles, ready whenever you are. The trial is free.

Affiliate link — we may earn a commission at no cost to you.

Long listen ahead?

While that generates: Audible starts instantly, keeps your place for weeks, and every title is narrated by a person. The trial is free.

Affiliate link — we may earn a commission at no cost to you.

Making a video?

Create videos from your ideas with InVideo AI.

Affiliate link — we may earn a commission at no cost to you.

How it works

Unlimited TTS reads any text aloud in your browser. There is no word or character limit, and you don’t need an account.

  1. Add your text. Type, paste or dictate it, or import a document.
  2. Choose Quick or Natural, and a speed. Quick uses the voices already on your device and starts at once; which voices you see depends on your device and browser. Natural uses lifelike AI voices that run privately in your browser. The first time, it downloads the voice model (about 380 MB) and saves it for next time.
  3. Listen or download. Press play to hear text of any length for free, or download it as a WAV file made with a Natural voice.

Drag to move through the text. Natural audio can be scrubbed after generation.

Have a document? Use the import button beside the text box, or drop a file onto the page, to have PDF, Word (.docx), ODT, EPUB, RTF, Markdown and text files read aloud. Files are read on your device and never uploaded. More about PDF to speech.

Voices & Languages

Theoretical maximum: 100 + languages and 300 + voices if every OS pack, browser-provided online voice pack, and third-party engine is installed.

Typical setups expose 40-60 languages and 120-200 voices. Check the dropdown above to see what your device supports.

Why does the number change?

speechSynthesis.getVoices() displays voices that your browser can access. Install extra voice packs, refresh this page, and they appear automatically.

What people use it for

  • Audiobooks: turn an ebook or a long document into audio. Import an EPUB, PDF or Word file and listen to the whole book, with no length limit.
  • Proofreading: hear your own writing read back to catch typos and clumsy sentences.
  • Study and documents: listen to articles, notes and reports instead of reading them on screen.
  • Narration drafts: try out a script for a video, slides or a podcast, then download the audio.

Need to talk with someone in another language? The Voice Translator is a separate tool that translates a spoken conversation both ways.

Privacy first

Where does your text go?

Privacy by mode — what stays local and what may be processed online:

ModeProcessingPrivacy
Device voices (Quick)Web Speech APIFully local
Browser-supplied online voices (if available)Browser/provider cloud serviceText may be sent to provider servers
AI mode (Natural)Supertonic TTS-3 in browser (WebGPU/WASM)Fully local after model download
  • Device voices (Quick): fully local via Web Speech API.
  • Some browsers may provide online voices; using those may send text to provider servers.
  • AI mode (Natural): processes text directly in your browser; fully local after model download.
  • Audio is streamed straight to your speakers and never stored by us.
  • Imported documents (PDF, Word, EPUB and more) are read in your browser; the file is never uploaded.
  • Open-source — audit the code on GitLab.

Add more voices on your device

Windows 10/11

  1. ⚙️ Settings → Time & Language → Language & region.
  2. Click Add a language → Install Speech.
  3. For premium "natural" voices: Settings → Accessibility → Narrator → Add natural voices.

macOS 12 +

  1.  System Settings → Accessibility → Spoken Content → System Voice.
  2. Click Manage Voices…, tick extra voices, then Download.

iOS / iPadOS

  1. Settings → Accessibility → Spoken Content/read & speak → Voices.
  2. Select a language, tap the ⬇ icon beside any additional voice to download, make sure to pick a premium or advanced voice to get the best sound quality.

Android

  1. Settings → Accessibility → Text-to-speech output (wording may differ).
  2. Tap the gear next to Preferred engine → Install voice data.

Browser online voices (if available)

Some browsers may expose additional online voices depending on version, platform, account, and region.

Frequently asked questions

Is there a word or character limit?
No. There is no word limit and no character limit. Paste, type or import text of any length — a paragraph, a long article or a whole book — and it is read aloud in full.
How do I install new text-to-speech voices on Windows 10/11?
  1. Go to Settings → Time & Language → Language & region.
  2. Click Add a language and install speech for your chosen language.
  3. For premium "natural" voices: Settings → Accessibility → Narrator → Add natural voices.
How do I add more voices on macOS 12 or later?
  1. Open System Settings → Accessibility → Spoken Content → System Voice.
  2. Click Manage Voices…, tick extra voices, then click Download.
How do I install new voices on iOS or iPadOS?
  1. Go to Settings → Accessibility → Spoken Content → Voices.
  2. Select a language, then tap the ⬇ icon beside any additional voice to download.
How do I add more voices on Android?
  1. Go to Settings → Accessibility → Text-to-speech output (wording may differ).
  2. Tap the gear next to Preferred engine and select Install voice data.
How do I access browser-supplied online voices?
Availability varies by browser, OS, account, and region. If your browser provides online voices, they appear automatically in the list.
Are AI voices private and secure on Unlimited TTS?
Yes. AI voice generation runs directly in your browser, so your text stays on your device in AI mode. This helps protect privacy and avoids server-side storage.
Can I download the audio?
Yes. Press Download audio to save a WAV file made with a Natural voice. The audio is generated in your browser, on your device.
Can Unlimited TTS read a PDF or Word document aloud?
Yes. Click the import button beside the text box, or drop a file onto the page. PDF, Word (.docx), OpenDocument (.odt), EPUB, RTF, Markdown, HTML and plain-text files are supported. The text appears in the box, ready to play with any voice or download as audio. Scanned PDFs without selectable text cannot be read.
Are imported documents uploaded to a server?
No. The file is read in your browser on your own device and is never uploaded. Only the extracted text is placed in the text box.