Introducing Speak Mode: AI Voice Translation That Speaks For You in Meetings

There is a specific, painful moment that every non-native speaker in a multilingual meeting knows. The discussion is moving quickly. Captions are scrolling on your screen. You understand everything perfectly — Gaavala has been translating the other side for twenty minutes and you are following along word by word. Someone turns to you and asks a direct question.

And then the language barrier, which had been one-way, becomes a wall.

You know the answer. You know exactly what you want to say. You simply cannot say it at the same speed and precision in the meeting's working language. You hesitate, soften, simplify, and end up sounding less informed than you are. By the time you assemble a careful sentence, the conversation has moved on.

We built Speak Mode to close that loop. With Speak Mode enabled, you speak in your native language and Gaavala speaks your translated voice back into the meeting. The other participants hear a fluent, real-time voice delivering your response in their language. You stop being the quiet person in the room.

This post walks through exactly what Speak Mode does, the single button that drives it and the two gestures it reads, the two voices you can choose between — 69 studio presets or a native clone of your own voice — and the tradeoffs you should understand before enabling it for a high-stakes call.

What Speak Mode Actually Does

Speak Mode is not a dubbing track layered on top of a transcript. It is a live, bidirectional voice pipeline that runs alongside the existing Gaavala transcription flow.

When you activate it during a meeting, the following happens inside your browser:

Your microphone audio is captured by the extension — separately from the tab audio Gaavala already captures for the incoming side.
That microphone audio streams directly to Soniox over a WebSocket for speech-to-text. This is the same direct-to-Soniox pattern the rest of Gaavala uses — no audio touches our backend.
As Soniox emits committed tokens in your source language, the extension batches them into short phrases and sends the text to Gaavala's translation step for the target language you configured.
The translated text is handed to your selected TTS engine, which synthesizes a voice clip.
That voice clip is sent into the call in place of your outgoing microphone track, so everyone hears the translated voice as if it were your own. There is no virtual microphone device to install and nothing to select in your meeting app's audio settings — and while the translated voice is playing, your real microphone is muted so the call never hears both at once.

The whole loop runs while you are still speaking. By the time you finish a sentence in your language, the synthesized translation is already playing out in theirs. You do not wait for a "translate" button. You do not pause between thoughts longer than you normally would.

One Button That Reads the Gesture

Real meetings are not all alike, so Speak Mode has to behave differently when you are firing back a one-line answer and when you are walking someone through a slide. Most tools solve that with a mode selector you have to set before you need it — which means the moment you need the other mode, you are in the wrong one.

Gaavala has no mode selector. There is one Speak button, and it reads how you press it.

Hold it

Hold the button and you are talking only while you hold. Let go and the pipeline closes cleanly. This is the walkie-talkie gesture, and it is the safe one: you never accidentally broadcast a side comment, a cough, or a moment of thinking-out-loud. It is the right instinct for a quick interjection, for high-stakes calls where precision beats flow, and for any room where your microphone might pick up voices you did not intend to translate.

Holding also works from the keyboard — press and keep Space held for about a third of a second and it behaves exactly like holding the button.

Tap it

Tap the button instead and it opens a hands-free 60-second window. A ring counts the window down in minutes and seconds and turns amber for the last ten, so you always know how much of your turn is left without watching a clock. Speak naturally; Gaavala translates and voices each phrase as you go, and you never touch anything.

Two quick taps open a 30-second window instead — the honest length for a short prepared point. Tap once more while a window is running and it stops early; otherwise it ends by itself at zero.

Why this is one control and not two

The gesture you already make encodes the intent. A short press means "just this", a tap means "give me a stretch". Nothing has to be configured in advance, nothing is in the wrong mode when the moment arrives, and there is no hotkey to bind or forget. The safety property people liked about push-to-talk — nothing leaves the room unless you meant it — is still exactly true of holding.

The Voices: 69 Studio Presets and Your Own

Speak Mode gives you two ways to choose the voice the meeting hears. Both speak all 60 languages Gaavala translates, and both stay on the same direct-to-Soniox path the rest of Gaavala uses — no third-party voice vendor in the loop.

69 Soniox studio voices (Pro default)

Soniox studio voices are the default on Pro and the one most people never need to change: 69 multilingual presets that speak all 60 languages Gaavala translates, cross-lingually, with a managed key — there is nothing to set up. Synthesis goes browser-direct to Soniox using the same short-lived-key pattern as captions, so the translated text never passes through Gaavala's backend. Latency is streaming — the voice starts playing as soon as the first chunk is ready, typically a second or two after a phrase commits.

Your own voice (native clone)

Record about 20 seconds of your own speech once, in the side panel, and Gaavala builds a personal voice clone — Soniox-powered — that speaks the same 60 languages a studio voice would, in your own timbre instead of a preset. The reference sample is stored encrypted, and you can delete it at any time from the same settings screen; your meeting audio itself is never stored, on this feature or anywhere else in Gaavala.

The two options trade off exactly one thing: familiarity. A studio voice sounds polished and neutral from the first session. Your own clone takes twenty seconds to set up and then sounds unmistakably like you, every time — useful if you run recurring calls with the same clients or teammates and want them to hear the same voice call after call.

How It Compares to What Else Is Out There

Real-time voice translation in meetings has been a "coming soon" feature for years. A few things exist, but none of them cover the same ground Speak Mode covers.

Microsoft Teams Interpreter Agent. Microsoft announced an Interpreter Agent for Teams that can translate and speak with a user's voice. It is Teams-only. It requires a Microsoft 365 Copilot license — a paid per-seat add-on on top of a qualifying base plan — and it is gated to tenant admins who have enabled Copilot for the organization. If you live inside a Copilot-licensed Teams estate, it is a legitimate option. If you work across Teams, Zoom, Meet, and Webex with customers outside your tenant, it will not help.
ChatGPT Voice Mode. ChatGPT can hold a voice conversation with you, and it can translate. What it cannot do is sit inside your Zoom call and speak on your behalf to other participants. It is a personal voice chatbot, not a meeting voice agent.
Google Meet translated captions. Google Meet has real-time translated captions. They are text-only. There is no spoken output on the other side.
Interprefy, KUDO, and enterprise interpretation platforms. These are real interpretation services — human interpreters, mostly, sometimes with AI assistance — priced and structured for large conferences and regulated industries. They are not something an individual consultant adds to a one-on-one sales call.

As far as we can tell, there is no consumer-priced tool in the market that does genuinely two-way voice translation inside the meeting platforms people actually use. Speak Mode is our answer to that gap.

Who Speak Mode Is For

Speak Mode is a Pro feature and it is priced for individual professionals, not enterprise deployments. The people who get the most out of it are:

International consultants running project calls with clients whose English is limited and who would rather hear you in their own language than struggle through yours.
Multilingual team leads joining standups with offshore engineering teams, where half the team thinks in one language and half thinks in another.
Sales reps selling into foreign markets where a fluent-sounding voice in the customer's language changes how the call feels and how the quote lands.
Field operations people bridging between an offshore site and HQ, where the stakes of a misunderstanding are operational, not just social.

If your meetings are fully bilingual in a single pair and everyone can keep up, you probably do not need Speak Mode. If there is a recurring moment where you or someone on the other side falls silent because the language gap is one-way, this is the feature that fixes that moment.

Privacy: What Changes and What Does Not

Gaavala's core privacy architecture does not change when you enable Speak Mode. Incoming meeting audio still streams directly from your browser to Soniox over a WebSocket that never touches our backend. Your microphone audio for Speak Mode follows the same direct-to-Soniox pattern — we never see it.

The TTS step follows the same pattern for both voice options. Soniox studio voices send the translated text browser-direct to Soniox, authenticated with the same short-lived temporary keys captions use — Gaavala's backend never sees the text or the audio. Your own cloned voice synthesizes the same way, with one deliberate, narrow exception upstream of it: the ~20-second reference sample you record to build the clone is stored encrypted (AES-256-GCM) on Gaavala's servers, used only to build and maintain your voice, and deletable on request at any time. Nothing else about Speak Mode's audio — not your microphone input, not the meeting audio, not the synthesized output — is ever stored.

Gaavala's backend remains outside the audio path for both voice options. If you want to verify this, the same network inspection trick from our privacy post still works: open the extension's background page DevTools, filter the Network tab, and you will see a direct connection to Soniox — and no audio traffic to gaavala.com.

How to Enable It

Speak Mode is a Pro-only feature. Gaavala's free trial (one-time 5 minutes, no credit card, never resets) does not include Speak Mode, so the setup flow goes roughly like this:

Install Gaavala from the Chrome Web Store free and sign in.
Upgrade to Pro from the side panel — $19.99/month, no trial period — upgrade directly when you need Speak Mode.
Open the side panel settings and find the Speak Mode section.
Choose a voice. Soniox studio voices are the default on Pro and need no setup. If you want to speak in your own voice, choose "Clone my voice" and record a ~20-second sample — Gaavala builds your clone and you can select it moments later.
Configure the target language for the meeting. There is no capture mode to pick — the Speak button reads your gesture, so nothing has to be decided in advance.

Then join a meeting. Hold the Speak button when you want to say one thing, or tap it for a hands-free window when you have a stretch to deliver.

Real-World Usage Tips

A few practical notes from building and dogfooding this:

Warm up by holding. The first time you hear your synthesized voice play into a meeting, it will feel strange. Hold the button for your first few calls before you start tapping for hands-free windows. Your sense of when to pause, how loud to speak, and how the translated voice lands on the other side all calibrate quickly — but only if you are in control of each burst.
Clone your own voice only. The side panel's recording flow only builds a clone from a sample you record of yourself — there is no path to cloning someone else's voice through Speak Mode, and the in-app consent step reflects that.
Disclose if it matters. If your meeting has compliance implications — legal, medical, regulated sales — tell the other side that a real-time voice translation layer is in the call. It is the same etiquette as disclosing a transcription tool.
Keep the native audio on. Gaavala still pipes the original meeting audio to your speakers. You should still be listening to and reading the incoming side. Speak Mode is the outgoing half, not a replacement for understanding what is being said to you.

FAQ

Does the meeting know I am using it? Not directly. The synthesized voice arrives on the other side through the same microphone channel you would use yourself, so there is no banner or metadata. The other side hears a very fluent voice and may notice small pauses before each response. We recommend disclosing it when it matters — see the etiquette note above.

Can I use my own cloned voice? Yes — natively, on Pro. Record a ~20-second sample in the side panel's Speak Mode settings and Gaavala builds a Soniox-powered clone you can select as your Speak Mode voice. No separate account or API key required.

What is the latency? Both the studio voices and your own clone use the same streaming, browser-direct-to-Soniox synthesis path. Expect the voice to start playing within a second or two of a phrase committing — you are not waiting for the whole sentence to render before the meeting hears anything.

What if my target language is not English? Both voice options already speak all 60 languages Gaavala translates — the Soniox studio voices and your own clone work the same way regardless of target language, out of the box.

Does it work in Teams Premium meetings? Yes. Speak Mode works in any meeting that runs in a Chrome tab, including Microsoft Teams, Zoom, Google Meet, and Webex. It does not matter whether the meeting organizer has Teams Premium or Copilot. Speak Mode runs on your side of the call, not on the meeting host's infrastructure.

Try It

Speak Mode is available right now to Pro subscribers. If you are new to Gaavala, start on the one-time free trial — 5 minutes of transcription, no credit card required — so you can evaluate the incoming translation experience first. Speak Mode is not included in the free trial; upgrade to Pro ($19.99/month, no trial period) when you are ready to unlock it on the outgoing side.

Add Gaavala to Chrome →

Install Gaavala from the Chrome Web Store free, then upgrade to Pro to unlock Speak Mode.