Privacy-first Voice to Text

Speak. Release.
Instant Text.

A native desktop application that converts your voice to text with zero latency. Hold a global hotkey to record, release to transcribe straight into your active window.

Lightning Fast

Written in native code for maximum speed and efficiency. Utilizing GPU acceleration where available, OiPer transcribes speech almost instantaneously.

100% Private

Audio and logs stay on your device.

Deep Control

Configurable LLMs & local/online optimization.

Unmatched Speed

We benchmarked OiPer against leading cloud and local alternatives. Our native desktop architecture processes a 30-second audio clip in just 1.5 seconds.

OiPer Desktop1.5s
Lemonfox API3.27s
Python Faster-Whisper3.55s
OpenAI Whisper API6.46s

Power User Configuration

OiPer adapts to your workflow. Whether you want a fully offline experience or highly accurate LLM-based online text optimization, the choice is yours.

1

Speech & Model Management

Select from various model sizes depending on your hardware capability. Auto-detect, CPU-only, or full GPU acceleration.

2

Bring Your Own Key

Configure custom base URLs and API keys for online providers if you wish to use cloud models. Enabled only when you choose.

Advanced LLM Support

Connect your preferred LLM (like Gemini 2.5 Flash Lite) to process transcribed text before injection. Perfect for formatting code, specialized terminology, or writing specific structures.

> model: "gemini-2.5-flash-lite"
> mode: "online-cleanup"
> status: "ready"
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