Voice-to-Text — Privacy First

Your Voice.
Your Machine.
Your Words.

OiPer Desktop transcribes speech to text at native speed — entirely on your device. Hold a hotkey, speak, release. Done in 1.5 seconds.

1.5s
Transcription Time
30s audio
100%
On-Device Processing
Zero cloud
2.18×
Faster than APIs
Benchmarked

Experience

A workflow that becomes invisible. Hold, speak, release — and you're done.

Performance

Native code. GPU acceleration. Results in 1.5 seconds. Not a round-trip.

Privacy

No telemetry. No cloud by default. Your audio stays exactly where it should.

What It
Does

Six capabilities that work in concert to make voice transcription feel effortless.

01

Press & Release

Hold any global hotkey to begin recording. Release to transcribe. An interaction so natural it disappears.

02

Purely Local

Whisper runs on your own hardware. Your voice, your words, your machine — never surrendered to a server.

03

Instant Injection

Transcribed text arrives in your active application. No clipboard, no paste, no interruption.

04

GPU Accelerated

CUDA and Metal support built in. Leverage your graphics card for inference that feels instantaneous.

05

Optional Refinement

Engage any LLM — local or cloud — for text cleanup. Always opt-in, always under your control.

06

Model Freedom

Choose your Whisper model. Tiny for speed, Large for precision. Download and switch from within the app.

Performance — 30s English Audio

Faster Than
Any API.

OiPer processes 30 seconds of English audio in just 1.5 seconds — more than twice as fast as the closest API competitor, while keeping your data entirely on-device.

Written in native code
GPU-accelerated inference
Zero network latency
OiPer Desktop1.5s
Lemonfox API3.27s
Python Faster-Whisper3.55s
OpenAI Whisper 1 API6.46s

Built for
Privacy

Your data is not a product. OiPer is designed from the ground up to keep everything on your device.

Default

Local Transcription

Whisper runs on your own CPU or GPU. No model API, no server, no exposure of any kind.

Default

On-Device Logs

Activity history and raw audio are stored locally. You choose what to keep and what to delete.

Optional

Cloud Refinement

Text cleanup via external LLMs is entirely opt-in. Supply your own API key. Disable anytime.

Begin Today

Speak Freely.
Stay Private.

No subscription. No cloud dependency. A single download and your voice becomes your fastest input.

codex 1codex 2codex 3codex 4codex 5
codex2 1codex2 2codex2 3codex2 4codex2 5
gemini 1gemini 2gemini 3gemini 4gemini 5
glm 1glm 2glm 3glm 4glm 5
sonnet 1sonnet 2sonnet 3sonnet 4sonnet 5
kimi 1kimi 2kimi 3kimi 4kimi 5
codex53 1codex53 2codex53 3codex53 4codex53 5
opus 1opus 2opus 3opus 4opus 5
qwen 1qwen 2qwen 3qwen 4qwen 5
sonnet2 1sonnet2 2sonnet2 3sonnet2 4sonnet2 5
lovable 1lovable 2lovable 3lovable 4lovable 5
v0 1v0 2v0 3v0 4v0 5