More free audio tools
Same quality bar. Still free. Still no upload.
Your files never leave your device
This is not a promise about how carefully we handle your upload. There is no upload. The file you choose is read into memory by your own browser, processed there, and handed back as a download — the tool has no server component and makes no network request with your data.
- Nothing is stored. We never receive the file, so there is no copy to retain, no retention period to disclose, and nothing to delete on request.
- Nothing is transmitted. No upload endpoint, no analytics payload carrying file contents, no third-party processor.
- You can verify it. Load this page, disconnect from the internet, and use the tool. It still works, because everything it needs is already on your machine.
- Nothing persists after you close the tab. Files are held in page memory only — not in local storage, not in a cache, not in a database.
A note on wording, because it matters: we do not describe these tools as “encrypted.” Encryption protects data that travels to somebody else's computer. Your file does not travel, so there is nothing to encrypt and nothing to intercept — which is a stronger guarantee than encryption, not a weaker one. The page itself is served over HTTPS like the rest of the site.
This makes the tools safe for material you are contractually barred from uploading to third-party services — client footage under NDA, unreleased campaign assets, anything covered by a confidentiality clause.
How it works
1. Paste a short hook
Soft cap around 400 characters so the line stays punchy for Reels and Shorts.
2. Pick a stock voice and speed
Curated American and British voices from Kokoro. No custom voice upload.
3. Generate on your device
WebGPU when available, otherwise WASM. First run downloads Kokoro ONNX into browser cache from Hugging Face.
4. Preview and download WAV
Play in the page, then download 16-bit PCM WAV. Nothing is uploaded to Versely.
Questions
What license are the model and voices under?
kokoro-js and the onnx-community/Kokoro-82M-v1.0-ONNX weights are Apache-2.0. Voices here are the stock generic American and British voices shipped with Kokoro (for example Heart, Bella, Michael, Emma). They are not celebrity clones and this tool does not clone a voice from your audio.
How big is the first download?
First run downloads Kokoro ONNX assets from Hugging Face into this browser cache. Plan on roughly 80 to 100 MB for the q8 WASM path. WebGPU with fp32 is larger. Later runs reuse the cache when the browser keeps it.
Do I need WebGPU?
No. WebGPU is preferred when the browser supports it (fp32). If it is missing or fails, the tool falls back to WASM with q8. WASM is slower but still on-device.
Does my text or audio upload to Versely?
No. Synthesis runs in your browser. Text stays in memory on your device. The only network traffic for this free tool is the first-run model download from Hugging Face (and normal page assets). This is not the paid Versely TTS credit path.
Is this a voice cloning tool?
No. You can only pick stock Kokoro voices. There is no custom voice upload, no speaker embedding from your audio, and no clone training.
Do my files get uploaded anywhere?
No. This free tool runs entirely in your browser using the Canvas and File APIs. The file you choose is read into memory on your own machine, processed there, and offered back as a download. Nothing is sent to a server, which is also why it keeps working with your network off.
Is it actually free, or is there a catch?
Actually free, with no account and no limit, because it costs nothing to run. The work happens on your device rather than on our hardware. That is different from generating with an AI model on Versely, which does cost credits. There is no free tier for generation.
Related tools
Stay in the same job cluster. Free tools stay on-device; paid tools are labelled as such.
These rearrange files. Versely makes new ones.
Everything on this page works on a file you already have, which is why it costs nothing. Generating something that did not exist (video from a prompt, a voice, a score) runs a model, and that costs credits.