Telvr — Speech to Text Desktop App. Speak, Insert, Done.
Speak
Insert
Done
Your voice,
wherever your
cursor is.
VOICE-TO-TEXT/DIRECT INSERT/AI ENRICHMENT/EVERY APP
speaking is
FASTER.
3-5x
People speak faster than they type
0detours
Your spoken text appears right where your cursor is
7modes
From email to meeting notes — your text in the right format and tone
PRESS
SPEAK
DONE
more thanDICTATION.
Hotkey
⌥ Option+Space
PRESS
ONEHotkey
ZEROApp switches
ZEROCopy-paste
Speak. AI listens.
SPEAK
LIVE“uhm hey Tobi yeah I’m not gonna make it today. So can we move the appointment to tomorrow, no day after tomorrow 1 pm? Does that work for you”
WHISPERTranscription
100+Languages
<2sLatency
No copy-paste.
DONE
Cleanup
Hey Tobi, I’m not gonna make it today. Can we move the appointment to the day after tomorrow, 1 pm? Does that work for you?
Not just
transcribed.
REFINED!
6 different
OUTPUT FORMATS.
Remove fillers. Fix grammar. Add punctuation.
INPUT
“uhm hey Tobi yeah I’m not gonna make it today. So can we move the appointment to tomorrow, no day after tomorrow 1 pm? Does that work for you”
CLEANUP
Hey Tobi, I’m not going to make it today. Can we move the appointment to the day after tomorrow, 1 pm? Does that work for you?
Roadmap
NEXT
IN DEV
App Detection
Context Awareness — Telvr detects the active app and automatically adjusts the enrichment mode.
PLANNED
Mobile Apps
iOS & Android with native keyboard integration. Telvr as a system-wide keyboard.
COMMUNITY
Self-Hosted
Community Edition with your own API key. Full control, open-source core.
on every
DEVICE.
Windows
Linux
IN DEVELOPMENT
iOS
PLANNED
Android
PLANNED
Start with
YOUR VOICE.
POPULAR
Pay-as-you-go
3 EUR /mo
+ usage-based costs
14 days free
Up to 3 EUR usage value
Test everything, risk-free
Start Freefrequently asked
FAQ
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.
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.
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.
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.
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.