Free Voice Cloning, No Upload | PocketWebTools
1. Reference voice
Drop an audio file, or click to choose<br>A short clip of one speaker, up to 20 MB
or
Record from microphone
A clean 5-20 second clip works best — one speaker, minimal background noise.
2. Text to speak
0 / 2,000
Expressiveness0.50
Higher values sound more intense and speak faster.<br>I own this voice, or have the speaker's permission to clone it.Cloning a voice without consent may be illegal where you live. This runs entirely in your browser, so we can't verify consent — that's on you.
Generate speech<br>Stays on your device. The voice model runs in your browser with WebGPU (or WebAssembly fallback). Your reference clip, your text, and the generated audio never leave your device. No upload, no signup, unlimited use.
Free voice cloning that runs in your browser<br>Record or upload a short clip of a voice, then generate new speech in that voice from any text, without uploading a single sound to a server. This tool runs Chatterbox, an open-weight zero-shot voice cloning model from Resemble AI, entirely inside your browser using WebGPU with a WebAssembly fallback. No account, no API key, no per-minute fee, and nothing ever leaves your device.<br>The same engine drives both privacy and price. Because the model lives in your browser, we have no inference bill to recover, no logs to keep, and nothing to upsell. Once the model is cached it even works offline.
How to use it<br>Record a 5 to 20 second clip from your microphone, or upload an existing one.<br>Wait for the reference voice to encode. The first run also downloads the voice model once, after which it is cached.<br>Type or paste up to 2,000 characters of text.<br>Adjust the expressiveness slider if you want a more animated delivery.<br>Confirm the consent checkbox, then click Generate speech.<br>Play it back in the built-in player and download the WAV when you are happy.
What it is good for<br>Narrating a video or presentation in your own voice without re-recording every revision, creating personalized voice messages, dubbing your own voiceovers into new scripts, and accessibility use cases like preserving a voice for someone who may lose the ability to speak. Because the audio is a plain WAV file, it drops straight into any video editor or audio tool, and there is no usage cap to work around.
Use it responsibly<br>Voice cloning is powerful, and that power cuts both ways. Only clone your own voice, or a voice you have explicit permission to clone. This tool has no server and no account, which means privacy for you, but it also means there is no one checking consent on the other end. That responsibility is yours. Impersonating someone without their permission can be illegal depending on where you live, independent of which tool was used to do it.
Private and free, by design<br>Cloud voice-cloning services upload your audio to their servers, meter you per character or minute past a small free tier, and require an account. This tool does the opposite. The model runs on your own hardware, so your voice sample never leaves the browser, there is nothing to log, and there is no bill to pass on to you. Chatterbox and its ONNX export are MIT licensed.<br>Want a text-to-speech tool with a curated set of ready-made voices instead of cloning your own? Try Text to Speech, which also works on iPhone.
Frequently asked questions<br>Does my voice sample get uploaded anywhere?No. The reference clip you record or upload, the text you type, and the generated audio all stay in your browser the entire time. Chatterbox, the voice model, runs locally with WebGPU (or WebAssembly on devices without it), so there is no server in the loop and nothing for us to log or retain.<br>How much reference audio do I need?A clean 5 to 20 second clip of one person talking, with minimal background noise or music. Longer clips do not meaningfully improve the result and just take longer to process. Record straight from your microphone or upload an existing recording.<br>Why does it download a model the first time?For the cloning to happen on your device, the neural voice model has to live on your device. The first time you submit a reference clip, your browser downloads Chatterbox (about 1.5 GB) and caches it. After that, every generation uses the cached copy and starts instantly. You can review or delete cached models from the 'Local models' chip in the page header.<br>Is a 1.5 GB download really necessary?Zero-shot voice cloning needs a larger model than a fixed-voice text-to-speech tool because it has to understand and reproduce an arbitrary, never-seen-before voice from a short sample, not just play back one of a small number of pre-trained voices. It is a one-time download, cached by your browser, and it never touches our servers.<br>What is the expressiveness slider?It controls exaggeration, a Chatterbox-specific control for how intense and animated the delivery sounds. Higher values add more emotional range and speed up the speech slightly; the default of 0.5 works...