Free Text to Speech + Download

Your text

0 characters · 0 words

1 · Preview (natural browser voices)

Voice

Speed: 1.0× Pitch: 1.0

Preview uses your browser's built-in voices (Web Speech API) — the most natural sound, free. Note: browsers can't save this audio to a file, which is why downloads use the offline engine below.

2 · Download audio file (WAV, unlimited)

Honest note: the downloadable file is generated by an offline synthesis engine (meSpeak.js, an eSpeak port) running entirely in your browser — it sounds robotic, not like the natural preview voices. The trade-off: it's 100% unlimited (no 20k-chars/week caps, no captchas, no accounts) and fully private. If you need studio-quality voices, that's what paid tools sell — we won't pretend this is that.

Offline voice

Speed: 175 wpm Voice character

First generation downloads the voice engine (~1 MB, one-time, cached by your browser). Long texts are split into chunks and stitched into a single WAV automatically.

Frequently asked questions

Why does the downloaded file sound robotic while the preview sounds natural?

Two different engines. Preview uses your operating system's built-in voices through the browser's Web Speech API — natural, but browsers provide no way to save that audio to a file (any site claiming otherwise is faking it). Download uses meSpeak.js, an offline eSpeak-based synthesizer that runs 100% in your browser — robotic, but it can actually render audio to a WAV file, unlimited and private. We show both honestly instead of pretending one engine does everything.

Is there really no character limit?

Correct — no weekly/monthly caps (unlike TTSMaker's ~20k chars/week or ElevenLabs' ~10 min/month free tiers), no captchas per conversion, no account. Long texts are automatically split into chunks and stitched into one WAV. Very long documents just take longer to render.

What format is the download? Can I get MP3?

WAV (uncompressed, 22.05 kHz mono) — it plays everywhere and converts losslessly. We don't offer MP3 directly because MP3 encoding in-browser needs a patent-encumbered encoder; convert the WAV to MP3 with any free converter (or this hub's audio tools) if you need it.

Does it work offline?

After the first load, mostly: the preview needs your OS voices (already on your device), and the offline engine + voice files are cached by your browser after the first generation. The very first visit needs internet to fetch the page and the engine files from CDN.

Is my text uploaded anywhere?

No. Preview synthesis happens in your OS; WAV generation happens in your browser tab. Nothing is sent to any server — there isn't even a backend to send it to.

Can I use the audio commercially (YouTube, etc.)?

The offline engine is meSpeak.js (© Norbert Landsteiner), a port of eSpeak, both under the GNU GPL v3. Generated audio inherits no additional restrictions from us, but GPL-licensed synthesis may matter for some commercial uses — check the eSpeak/meSpeak license if you're producing commercial content. The natural-voice preview is your OS's voice; its license is your OS vendor's.