FAQ
Quick answers to the common questions.
Is it really free, with no word limit?
Yes. There's no sign-up, no character cap, no paid tier. Paste a tweet or paste a novel — same tool. We keep it free by showing ads.
Do you store the text I paste?
No. Quick TTS is entirely client-side. The text you paste is processed by your browser and never sent to any server of ours. We don't have logs of it because it never reaches us.
Your most-recent text is saved in your browser's localStorage so it's still there if you accidentally close the tab, but that's on your device only. Clear your site data to wipe it.
What's the difference between the default voice and "AI Voice"?
Default: your browser's built-in speech engine (Web Speech API). It's instant, works on every device, and sounds like a standard TTS voice. The exact voices available depend on your OS — Mac has Samantha, Windows has Zira and Natasha, Android and iOS have their own sets.
AI Voice: a small neural TTS model called Kokoro-82M that runs locally on your GPU via WebGPU. It sounds dramatically more natural — closer to a real human narrator than a robot. The trade-off is a ~80MB one-time download and a browser with WebGPU support (desktop Chrome or Edge today).
Does the AI voice send my text to a server?
No. Kokoro runs entirely in your browser using WebGPU. The only network requests are the initial download of the model (from Hugging Face) and the library (from jsDelivr). Everything after that — turning your text into audio — happens on your machine.
Does it work on mobile?
Yes, using your device's built-in voice. The AI Voice toggle is desktop-only right now because mobile GPUs don't reliably run Kokoro fast enough for real-time playback. We'll revisit when smaller models drop or mobile WebGPU gets faster.
Can I use the audio commercially (YouTube, podcasts, products)?
Yes, with one caveat: you should credit the underlying voice model in your project's credits or description.
- Browser TTS: uses your operating system's built-in voices. Microsoft, Apple, and Google publish their own terms for commercial use of system voices — generally permitted for incidental and small-scale use, but check their docs for your target voice if you're shipping at scale.
- Piper: the engine is MIT-licensed. We ship a curated set of voices: LibriTTS-R and VCTK are CC-BY 4.0 (commercial use OK with attribution), and Joe is CC0 / public domain (no restrictions). Attribution for CC-BY voices is typically satisfied with a line in your video/podcast description like "Voice by Piper TTS — LibriTTS-R / VCTK, CC-BY 4.0".
- Kokoro HQ: the model is Apache 2.0 licensed — commercial use is permitted. Apache 2.0 doesn't strictly require attribution but we recommend crediting Kokoro-82M in your project credits as good practice.
We don't claim any rights over the audio you generate. You're responsible for complying with the underlying model licenses in your specific use case.
How long can my text be?
As long as you want. We chunk the input and stream playback, so pasting a 50,000-word document works the same as pasting a sentence — it just takes longer to get through. On the AI Voice path, we pipeline generation with playback so there's no long wait up front.
Why does the first AI Voice play take so long to start?
The first time you enable AI Voice, your browser has to download the ~80MB model from Hugging Face. That takes a few seconds to a minute depending on your connection. After that it's cached in your browser, and all future uses are fast.
I'm on a work computer and AI Voice is stuck at "Downloading..."
Some corporate networks block jsDelivr or Hugging Face. If AI Voice never finishes initializing, that's almost always the cause. The default voice works without any external downloads.
Why do I see ads?
Ads are how we pay for the domain, the hosting, and the time to maintain the tool. That's the trade for keeping it free with no limits. If you hate ads, you have our respect — and a browser adblocker — at your disposal. We won't guilt-trip you.
Is my keystroke data tracked?
No. We don't run analytics or keystroke logging. See the Privacy Policy for the full rundown.
Something broke / I have feedback
Email hello@quick-tts.com. Include your browser and OS.