Speak Any Language in Your Own Voice — Native Voice Cloning in Meetings

Speak Mode already let you talk in your own language and have a synthesized voice deliver the translation into a meeting. Until now, the voice doing the speaking was either a studio preset or a voice you had separately cloned in your own ElevenLabs account. Today we are shipping the missing piece: Gaavala Pro can clone your own voice directly, from a sample you record in the side panel, and that clone speaks all 60 languages Gaavala translates. No ElevenLabs account, no API key, no third-party voice-cloning tool to set up first.

What Native Voice Cloning Actually Is

The idea is simple to state and took real engineering to make reliable: record about 20 seconds of your own speech once, and Gaavala builds a synthetic voice modeled on yours. From then on, when Speak Mode plays your translated sentence into a meeting, it can play it in that voice instead of a generic preset — in Japanese, Portuguese, Arabic, or any of the 60 languages Gaavala supports, cross-lingually, from the same single sample.

This is a Soniox-powered feature, not an ElevenLabs one. That distinction matters for two reasons. First, it means your personal clone is included as part of your Pro plan — there is no separate account to create, no per-character billing to track, no API key to paste into a settings field. Second, it means the sample never leaves the same direct-to-Soniox pipeline that already carries your meeting audio and your Speak Mode microphone input. We are not introducing a new vendor into the pipeline; we are extending the one already doing the transcription and translation work to also handle synthesis of your voice.

ElevenLabs bring-your-own-key voice cloning still works exactly as it did before, for anyone who already has voices cloned there and wants to keep using them. The native Soniox clone is a separate, additional option — not a replacement, and not a requirement.

How to Use It

Setting it up takes about a minute:

1. Open the Gaavala side panel and go to Speak Mode settings.
2. Choose "Clone my voice" as the voice option.
3. Record a short sample — about 20 seconds of normal speech is enough. Read a sentence or two out loud, in whatever language you are most comfortable in.
4. Gaavala builds your personal voice from that sample. Once it is ready, select it as your Speak Mode voice.
5. Join a meeting and use Push-to-Talk or Timed Speak as usual. Your translated sentences now play in your own cloned voice, in whatever target language the meeting needs.

You can re-record the sample at any time if you want to refresh the clone, and you can delete it entirely from the same settings screen whenever you choose.

The Privacy Model

A voice sample is not like a transcript or a meeting recording. It is biometric data — a physical characteristic that can identify you — and Gaavala treats it accordingly, with protections that go further than the rest of the product's already-direct audio pipeline.

Here is exactly what happens: your ~20-second sample is stored encrypted at rest on Gaavala's servers using AES-256-GCM. It is used for exactly one purpose — building and maintaining your personal synthetic voice — and for nothing else. It is never used for identification, never used for advertising, and never shared beyond the one purpose it exists for. The sample is processed by Soniox, our speech provider, to construct the voice model; Soniox does not receive it for any purpose beyond that.

This is a deliberate exception to how Gaavala handles audio everywhere else in the product. Your meeting audio and your Speak Mode microphone input are never stored on our servers — they stream browser-to-Soniox and are gone. Your voice-clone sample is different by necessity: for the clone to work session after session, something has to persist so your voice can be reproduced later. So we made that one exception explicit, narrow, and fully reversible: encrypted, purpose-bound, and yours to remove.

Deleting your voice clone is a single action in the side panel, and it does exactly what "delete" should mean — it removes the recording, the synthetic voice built from it, and the corresponding data held on the provider side. Nothing lingers after that. If your organization or your own habits call for periodically reviewing what data you have stored anywhere, this is designed to make that review trivial: one toggle, one confirmation, and it is gone.

Full details on retention, processing, and your rights around this data live in our Privacy Policy, under the voice-clone section — the same document that governs every other claim we make about how Gaavala handles your data.

Who This Is For

Native voice cloning is aimed at the same people Speak Mode already serves, with one added benefit: consistency. If you run recurring calls with the same clients, teammates, or partners across languages, hearing the same voice — your voice — every time removes a layer of unfamiliarity that a rotating studio preset never quite eliminates. International consultants, multilingual team leads running standups across offshore teams, and sales reps working foreign markets are the clearest fits, for the same reasons they already reach for Speak Mode: being understood, not just heard.

It is also a meaningfully lower-friction option than ElevenLabs BYOK cloning for anyone who wants a personal voice without maintaining a second vendor relationship. If ElevenLabs' broader language catalog or an existing cloned voice already fits your workflow, that path remains fully supported — this is an addition to Speak Mode's options, not a narrowing of them.

Native voice cloning is available now on Pro. Open Speak Mode in the side panel to record your sample and try it in your next meeting.