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 pay-as-you-go model: EUR 3 per month infrastructure fee plus EUR 0.03 per minute of usage. 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.

← Blog2026-02-15

Push-to-Talk Dictation: How to Set Up Hotkey-Based Voice Typing

Why Push-to-Talk Beats Always-On Dictation

Traditional dictation tools listen continuously or require you to click a button in a specific app. Push-to-talk changes the paradigm: hold a hotkey, speak, release, and your text appears exactly where your cursor is.

This approach solves three fundamental problems with voice input:

No accidental transcription — the microphone only activates when you press the hotkey
No app switching — works in any application, system-wide
No manual pasting — text is inserted directly at the cursor position

Step 1: Install Telvr

Download Telvr for macOS from the website. Windows support is in development.

After installation, create an account and you will receive EUR 3 starter credit — enough for approximately 100 minutes of voice typing.

Step 2: Configure Your Hotkey

Telvr defaults to Option + Space as the push-to-talk hotkey. This combination is ergonomic (left thumb on Option, right thumb on Space) and does not conflict with common shortcuts.

To change the hotkey:

Open Telvr preferences
Navigate to the hotkey settings
Click the hotkey field and press your preferred combination
Common alternatives: Ctrl+Shift+Space, Caps Lock (remapped), or a dedicated mouse button

Tips for choosing a hotkey:

Avoid combinations used by your most frequent apps
Choose keys you can reach without moving your hands from the home row
A two-key combination prevents accidental activation

Step 3: Choose Your Enrichment Mode

Telvr does not just transcribe — it processes your speech through AI enrichment modes. Before you start dictating, select the mode that matches your context:

Cleanup: Removes filler words, fixes grammar, adds punctuation. Best for general text input.
Email: Formats your speech as a professional email with subject line and greeting.
Meeting Notes: Structures your speech into bullet points with action items.
Summary: Condenses your speech into 2-3 key sentences.
Dev Task: Formats as a structured development task with context and acceptance criteria.
Custom: Use your own system prompt for personalized output.

For daily use, Cleanup mode covers 80% of scenarios. Switch modes when you need specific formatting.

Step 4: Start Dictating

The workflow is simple:

Place your cursor where you want text to appear
Press and hold your hotkey
Speak naturally — do not worry about fillers, pauses, or perfect sentences
Release the hotkey
Wait 1-2 seconds for processing
Your cleaned, formatted text appears at the cursor position

Speaking tips for better results:

Speak at a normal conversational pace
Complete your thought before releasing the hotkey
Mention punctuation explicitly if needed in raw mode (e.g., "comma", "period")
In enrichment modes, Telvr handles punctuation automatically

Step 5: Optimize Your Workflow

Once comfortable with the basics, optimize for speed:

Queue multiple insertions: Dictate one paragraph, move cursor, dictate the next
Mix with typing: Type code or structured content, dictate comments and documentation
Use mode switching: Keep Cleanup as default, switch to Email mode when writing messages
Leverage language detection: Telvr auto-detects your language — switch between languages mid-session

Common Use Cases

Email responses: Read an email, press hotkey, speak your reply, release. The email mode formats it with a subject line and professional tone.

Code documentation: Navigate to a function, press hotkey, describe what the function does. Cleanup mode produces clean documentation text.

Meeting follow-ups: After a meeting, press hotkey and summarize the key decisions. Meeting Notes mode structures everything with bullet points and action items.

Quick messages: In Slack or Teams, press hotkey, speak your message, release. Cleanup mode removes the "uhm" and "like" from casual speech.

Troubleshooting

Text not appearing? Check that your cursor is in an editable text field. Telvr simulates keyboard input, so the target field must accept text.

Poor accuracy? Ensure your microphone input is clear. External microphones outperform built-in laptop mics significantly.

High latency? Check your internet connection. Telvr processes audio in the cloud — a stable connection ensures sub-2-second responses.