Voice generation FAQ
Is voice generation free?
Yes, completely free. It runs in your browser, so there's no server cost — no usage caps, no time limits, and commercial use is welcome.
Are my voice and text uploaded to a server?
No. Your reference audio, input text, and generated audio are all processed in the browser. Nothing is uploaded to AudioBuff or to Resemble.
How long should my reference audio be?
At least 10 seconds, with 15–20 seconds recommended. Below 10s the voice characteristics extract unreliably; quality plateaus past 20s. Record in a quiet space at a natural pace for best results.
What languages does it support?
English only for now (Beta). We're tracking Resemble's Chatterbox Multilingual (23 languages, released December 2025) and will adopt it once the Transformers.js port lands.
Are generated clips watermarked?
No audio watermark is embedded in the sound. Instead, every exported WAV / MP3 records metadata stating that the audio is AI-generated (IPTC digital source type trainedAlgorithmicMedia). Converting the file with other software may remove it, so also disclose that the audio is AI-generated wherever you publish it.
Does it work on Safari or iPhone?
Not currently. iOS Safari and macOS Safari are unsupported because of a known bug in WebKit's WebAssembly compiler that crashes the runtime. Use a recent Chrome or Edge instead. WebGPU is preferred but a WebAssembly fallback runs everywhere else.
How big is the model download?
About 1.5GB on first load, then cached in your browser's IndexedDB so subsequent runs work offline. You can clear the cache from the model loader at any time.
Can I take the generated audio into the EQ editor?
Yes. After generation, click "Continue in audio editor" to hand the result off to the EQ / loudness normalization / MP3 export page. Cloning, finishing, and final delivery all happen in the same browser tab.
Can I clone someone else's voice?
Only your own voice or audio you have explicit permission to use. Cloning another person's voice without consent may violate laws like the US ELVIS Act, and the responsibility falls on you. If you publish in the EU, AI-synthesis disclosure is also required.