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.

← Blog2026-02-22

Write Emails 3x Faster with Voice Dictation

The Email Problem

The average knowledge worker spends 2.5 hours per day reading and writing email. That is roughly 30% of the working day, and most of it is composition time — sitting in front of a blank reply field, typing out thoughts that you could express verbally in a fraction of the time.

The math is straightforward: people type at 40-60 words per minute and speak at 130-160 words per minute. A 200-word email takes roughly 3-5 minutes to type and about 90 seconds to speak. Across dozens of emails per day, the time difference is significant.

The catch has always been output quality. Raw speech dictation produces text that reads exactly how people talk — with filler words, incomplete sentences, informal phrasing, and no formatting. You save time on input and spend it all again on editing.

AI enrichment solves that problem.

How Voice + AI Transforms Email Writing

The workflow with a tool like Telvr is different from traditional dictation:

Place your cursor in the email reply field
Select Email mode in Telvr
Hold the push-to-talk hotkey and speak your message naturally
Release the hotkey
Within two seconds, a properly formatted professional email appears at your cursor

You do not need to speak in perfect sentences. You do not need to think about formatting, subject lines, or greetings. You speak your thoughts — "tell Sarah the project timeline is slipping by two weeks, we need to reschedule the kickoff, suggest next Tuesday or Wednesday afternoon" — and the AI transforms that into a complete, professional email.

What the AI Enrichment Actually Does

The Email mode in Telvr does several things simultaneously:

Removes disfluencies: "Um," "uh," "like," and false starts are stripped out before they ever hit the text field.

Fixes grammar and punctuation: Run-on sentences get separated. Missing commas and periods appear. Verb agreement issues are corrected.

Adds professional structure: Depending on the content, the AI adds an appropriate greeting, organizes the body logically, and closes with a professional sign-off.

Adjusts tone: Informal phrasing gets elevated to professional register without changing the core message.

Generates a subject line: If no subject is present, the AI generates one based on the email content.

Before and After: A Real Example

What you speak: "Hey Mark, just wanted to check in on the Henderson contract, we were supposed to have the first draft by end of last week and I haven't seen it yet, can you let me know what's going on, ideally I need it by Thursday because the client is asking questions and I don't want to lose the deal"

What appears in your email client:

Subject: Henderson Contract — Draft Status Update

Hi Mark,

I wanted to follow up on the Henderson contract. The first draft was due at the end of last week, and I have not received it yet.

Could you let me know the current status? I need the draft by Thursday at the latest — the client has started asking questions, and I want to make sure we can respond promptly.

Thanks in advance.

Same information. Professional tone. Properly formatted. Ready to send with minimal review.

The Time Math

For a professional who sends 30 emails per day (a typical knowledge worker volume):

| Task | Typing | Voice + AI | |---|---|---| | Average email length | 150 words | 150 words | | Input time | ~3 minutes | ~70 seconds | | Editing time | ~1 minute | ~30 seconds | | Total per email | ~4 minutes | ~100 seconds | | 30 emails | ~2 hours | ~50 minutes |

The time savings is roughly 1 hour and 10 minutes per day. Over a five-day work week, that is nearly six hours reclaimed from email composition.

These numbers assume average typing speed. For slower typists, the gap is even larger. For faster typists, the absolute time savings is smaller, but voice still wins because the AI handles formatting automatically.

Workflow Integration Tips

Reply without switching focus: With system-wide insertion, you can dictate directly into Gmail, Outlook, Apple Mail, or any email client on your desktop. You do not need to switch to a separate dictation app.

Handle email queues faster: Open a message, press the hotkey, dictate your reply, release. Move to the next message. The push-to-talk pattern lets you process a queue of emails efficiently without lifting your hands off the keyboard.

Batch similar emails: If you need to send similar messages to multiple people, dictate the core content once, then quickly edit the recipient-specific details.

Review before sending: Even with AI formatting, spend 15-20 seconds reviewing the generated email before sending. The AI is highly accurate but you may want to adjust specific phrasing or add details you did not mention verbally.

Beyond Email: Slack, Teams, and Messaging

The same approach works for any text-based communication:

Slack and Teams messages: Shorter, more casual than email. Clean mode (rather than Email mode) works better here, removing fillers without over-formalizing.
Customer support responses: Template-like responses that benefit from consistent formatting.
LinkedIn messages: Professional but conversational — Email mode produces good output.

The key enabler in all cases is system-wide text insertion. Tools that require you to open a separate window to dictate and then manually paste into your email client add enough friction that most people abandon the habit. Push-to-talk with direct cursor insertion removes that friction entirely.

Getting Started

The transition to voice email writing takes about one week of deliberate practice:

Days 1-2: Dictate emails that you would normally type. Compare the output to what you would have written. Notice where the AI output is better or different.

Days 3-4: Start dictating replies within seconds of reading an email, without composing in your head first. Let the AI handle the structure.

Days 5-7: You will find yourself composing complete, professional emails in under two minutes without thinking about it. The workflow becomes as natural as speaking.

The goal is not to replace your writing instincts — it is to remove the friction between having a thought and that thought being expressed as professional text.