Press a hotkey anywhere on your system, speak naturally, and Telvr transcribes your voice in real-time using Whisper. The finished text is automatically inserted at your cursor position — no copy-paste, no app switching.

Which languages are supported?

Telvr supports 50+ languages via OpenAI's Whisper large-v3 model. Language detection is automatic — just speak in your preferred language and Telvr handles the rest.

Do I need a subscription?

No. Telvr uses a prepaid model with tiered pricing: from EUR 0.003 per minute at high usage, up to EUR 0.03 per minute when starting out. EUR 3 monthly minimum — your usage counts toward it. No lock-in, no auto-renewal. You top up your balance and use it at your own pace.

Does Telvr work offline?

Currently, Telvr requires an internet connection for cloud-based transcription via Groq. A Community Edition with local processing using your own API key is planned for the future.

Which apps are supported?

Telvr works system-wide — it inserts text at the cursor position in any application. Email clients, chat apps, code editors, browsers, word processors — if you can type in it, Telvr works there.

All data is transmitted via TLS encryption. Audio recordings are not permanently stored after transcription. Groq processes your audio under a Data Processing Agreement (DPA). We do not sell or share your data.

← All Use CasesWhatsApp2026-03-11

Voice-to-Text for WhatsApp Desktop: Type Less, Say More

The Problem

WhatsApp on mobile has voice messages built in. You press and hold, speak, release, and send. It is natural, fast, and effortless. Then you sit down at your computer and use WhatsApp Desktop, and suddenly you are back to typing.

Desktop users lose the voice message convenience for a simple reason: voice messages sent from desktop are audio files that recipients have to stop what they are doing to play. In many professional and personal contexts, a voice message is intrusive in a way that text is not. Recipients can glance at a text message in two seconds; a voice message demands headphones, quiet, and uninterrupted attention.

The result is that WhatsApp Desktop users type everything. Long updates, quick check-ins, replies to complex questions — all typed, on a keyboard, in a messaging app originally designed for mobile convenience. The messages are often shorter than intended, rushed, or riddled with autocorrect artifacts because typing quickly in a chat window invites errors.

How Telvr Works with WhatsApp Desktop

Telvr works with WhatsApp Desktop and the WhatsApp web version through system-level text injection. No WhatsApp integration is required. No access to your WhatsApp account. Telvr simply inserts text at the position of your cursor, and WhatsApp receives it as keyboard input.

The workflow is immediate:

Open WhatsApp Desktop and navigate to the conversation you want to reply to.
Click into the message input field at the bottom of the chat.
Press your Telvr hotkey and speak your message naturally.
Release the hotkey. Within under two seconds, the processed text appears in the input field.
Review and press Enter to send.

This gives you the speed and naturalness of a voice message with the discretion and convenience of text. The recipient gets a well-formatted message they can read instantly. You spent five seconds speaking instead of sixty seconds typing.

Best Enrichment Mode for WhatsApp: Clean and Correct

WhatsApp messages occupy a middle ground between formal email and ephemeral chat. The right tone is conversational but clear — not formal, but also not a stream of filler words and half-sentences. Clean and Correct mode is exactly calibrated for this.

When you speak a WhatsApp message through Clean and Correct, the AI:

Removes filler words ("um," "uh," "like," "you know") that are natural in speech but look sloppy in text
Corrects grammatical errors and incomplete sentences
Normalizes punctuation — adding periods and commas where your speech implied them
Preserves your conversational tone and personal voice

The output reads like a message you spent time typing carefully, even if you spoke it in ten seconds.

Clean and Correct is ideal for:

Updates to family or friends where you want to be clear but relaxed
Professional contacts on WhatsApp where a sloppy message would reflect poorly
Group chats where multiple people will read your message
Longer messages where typing would take too long but spoken rambling would be confusing

For very short messages — "Yes, sounds good" or "On my way" — there is no need for any enrichment mode. Just use Raw Transcription. Clean and Correct earns its value on messages of two sentences or more.

Before and After Example

Raw speech input:

"hey so uh I'm gonna be about fifteen minutes late to the lunch thing because I'm just finishing up a call and uh parking is always a nightmare in that area so maybe we can uh push the reservation back or just uh get a table and I'll join when I get there"

After Clean and Correct:

Hey, I'm going to be about fifteen minutes late. I'm just finishing up a call, and parking in that area is always difficult. Feel free to push the reservation back or go ahead and get a table — I'll join as soon as I arrive.

Raw speech input (professional contact):

"yeah so I've had a chance to look over the contract and uh most of it looks fine but I had a few questions about the payment terms and the uh liability clause in section four um could we maybe jump on a quick call this week to go through those"

After Clean and Correct:

I've had a chance to review the contract, and most of it looks good. I have a few questions about the payment terms and the liability clause in section four. Would it be possible to schedule a quick call this week to go through them?

Both outputs are clean, professional, and read as though they were typed carefully. The speaker spent less than fifteen seconds producing each message.

Time Savings

WhatsApp Desktop usage varies widely, but for people who manage personal and professional relationships through the app, thirty to fifty messages per day is realistic. The time cost of typing each message depends on length, but even at an average of forty-five seconds per message, that is twenty to thirty-seven minutes per day spent purely on typing.

With Telvr, the same messages take five to fifteen seconds of speaking. The processing and review adds another five seconds. The time savings per message is significant, and the aggregate over a week is measured in hours.

There is also a quality improvement. Spoken messages are longer and more complete than typed messages when typing is the bottleneck. People truncate their messages when typing is slow — leaving out context, nuance, and warmth that they would have included if speaking were an option. With Telvr, you say what you mean without the pressure to keep things short for typing convenience.

Getting Started

Download Telvr for macOS from telvr.ai and complete setup.
Configure your microphone input during the setup wizard.
Assign a hotkey that is easy to reach while your hands are at the keyboard.
Open WhatsApp Desktop and click into any message field.
Try Clean and Correct mode for your next multi-sentence message.

Telvr works across all your applications simultaneously. The same hotkey setup that improves your WhatsApp messages also handles email, Slack, Notion, and every other tool you use. One configuration, system-wide benefit.

New users get a €3 Welcome Credit to try all enrichment modes with no commitment. After that, you only pay for what you use — tiered pricing starts at €0.030 per minute and drops to as low as €0.003 per minute as your usage grows. No monthly minimum — less than the cost of a single cup of coffee, for a tool that saves time every single day.