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 CasesSlack2026-03-11

Voice Typing for Slack: Send Messages Without Typing

The Problem

Slack is supposed to make communication faster. In practice, it often does the opposite. Instead of fewer interruptions, you get more of them — just distributed across dozens of channels rather than a single inbox. And the expectation of quick, casual responses means you spend a surprising amount of time typing short messages.

The friction is subtle but constant. You switch to Slack mid-task, type a quick update, switch back. Thirty seconds here, a minute there. Over a workday, the context switching and typing overhead adds up to a significant block of time — time that was never allocated for communication but gets consumed by it anyway.

The challenge with Slack specifically is that messages exist on a spectrum: some need to be terse and punchy, others require a bit more context. Getting the tone right while also typing quickly enough to keep up with real-time conversation creates a small but persistent cognitive tax.

How Telvr Works with Slack

Telvr works with Slack's desktop app, the browser version, and any other Slack client on macOS — without any integration, plugin, or workspace permission. It inserts text directly at your cursor position through system-level text injection, which means Slack sees the text as if you typed it yourself.

The workflow for Slack is straightforward:

Click into a Slack message input field — a channel, a thread, or a direct message.
Press your Telvr hotkey to begin recording.
Speak your message naturally. You can speak at a normal conversational pace.
Release the hotkey. Within under two seconds, the transcribed and processed text appears in the Slack input field.
Review quickly and press Enter to send.

You stay in the Slack window throughout. There is no alt-tabbing to a transcription app, no clipboard operations, no reformatting required. The message is ready in the input field when Telvr finishes.

Best Enrichment Mode for Slack

Two modes work particularly well for Slack, depending on the type of message you are sending.

Clean and Correct is the go-to mode for most Slack messages. It takes your natural speech, removes filler words like "um," "uh," and "you know," fixes grammar, and normalizes punctuation — while preserving the conversational tone that Slack messages call for. The result reads like a well-typed message without requiring you to type it.

This mode is ideal for:

Status updates in team channels
Responses to questions
Quick clarifications or feedback
Direct messages where a natural tone is appropriate

2-3 Sentences works well when you need to give a concise update or summary. If you have been working on something for an hour and want to give the team a quick status, you can speak freely for thirty seconds and let Telvr compress it into a tight, readable summary that does not bury the key point.

For Slack's real-time nature, Clean and Correct will be your default. Switch to 2-3 Sentences when you catch yourself about to write a wall of text.

Before and After Example

Raw speech input (Clean and Correct mode):

"yeah so uh the API integration is mostly done I just need to write a few more tests um I think I'll have it ready by end of day tomorrow but maybe we should have a quick call to uh go over the edge cases before I push"

After Clean and Correct:

The API integration is mostly done. I just need to write a few more tests — I should have everything ready by end of day tomorrow. It might be worth a quick call to go over the edge cases before I push.

Raw speech input (2-3 Sentences mode):

"so I've been working on the dashboard redesign all morning and I went through the Figma file and made a bunch of changes to the layout and I think the card components now align better with the design system and I also updated the color tokens to match the new brand guidelines and generally I think it's looking a lot better"

After 2-3 Sentences:

Completed the dashboard redesign this morning. Updated the card components to align with the design system and refreshed the color tokens to match the new brand guidelines. Overall the layout is significantly improved.

The second example is the more dramatic transformation — raw stream-of-consciousness becomes a precise, scannable update in three sentences.

Time Savings

Slack message frequency varies widely by role, but for most team-based workers, sending thirty to sixty messages per day is not unusual. Each message might take only thirty to ninety seconds to type, but the aggregate is real.

More importantly, Slack has a rhythm problem. When you are in flow on a task and Slack demands a response, the context switch costs more than just the typing time. Research consistently shows that interruption recovery — getting back to the same depth of focus — takes several minutes. Anything that lets you respond faster and return to your primary task sooner is worth far more than the raw time saved.

Telvr's advantage in Slack is speed of response, not just speed of typing. Speaking a message takes a few seconds. Typing the equivalent often takes thirty to sixty seconds, especially if you re-read and adjust before sending. The faster you can close the loop on a Slack conversation, the sooner you can return to what you were doing.

For users who send a lot of Slack messages — managers, team leads, anyone in a cross-functional role — Telvr can recover thirty minutes to an hour per day in Slack alone.

Getting Started

Download Telvr for macOS from telvr.ai.
Install and configure your microphone input during setup.
Assign a hotkey that you can press with one hand while the other is on the mouse — you will want to keep Slack in focus.
Open Slack, click into any message field, and try your first dictation.
Set Clean and Correct as your default enrichment mode for casual communication.

Telvr works across all applications simultaneously, so the same hotkey and mode setup handles Slack, email, Notion, and every other tool in your workflow. You configure it once and it works everywhere.

New users get a €3 Welcome Credit to try all 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. A typical Slack-heavy workday uses well under ten minutes of transcription time.