Now entirely local and private

Your voice. Instantly typed.

Simply hold a global hotkey to record, release to transcribe, and the text is instantly injected into your active application. The fastest way to write, without sacrificing privacy.

Native app • macOS & Windows

Instant Injection

Press a hotkey to talk, release to transcribe. The text flows directly into wherever your cursor is.

100% Private

Transcription runs locally on your machine. Activity logs and audio stay on-device by default.

Native Speed

Built with highly optimized native code. Leverages GPU acceleration to transcribe almost instantly.

Blazing Fast Transcription

We benchmarked OiPer against leading cloud and local alternatives using a 30-second English audio sample. With native code and GPU optimization, OiPer leaves the competition behind.

Results measured on equal hardware configurations
OiPer Desktop 1.5s
Lemonfox API 3.27s
Python Faster-Whisper 3.55s
OpenAI Whisper 1 API 6.46s

You're in control

Configure everything from models to online services.

Local First

  • Backend Preferences (Auto/CPU/GPU)
  • Speech Model Management
  • All activity logs stay on-device

Optional Online Power

  • Custom Base URL Setup
  • Use your own API Keys
  • LLM Text Optimization (Gemini 2.5 Flash, etc.)
Codex-5.2 1Codex-5.2 2Codex-5.2 3Codex-5.2 4Codex-5.2 5
Codex-5.3 1Codex-5.3 2Codex-5.3 3Codex-5.3 4Codex-5.3 5
Codex-5.3 1Codex-5.3 2Codex-5.3 3Codex-5.3 4Codex-5.3 5
GPT-5.4 1GPT-5.4 2GPT-5.4 3GPT-5.4 4GPT-5.4 5
Gemini-3.1 Pro 1Gemini-3.1 Pro 2Gemini-3.1 Pro 3Gemini-3.1 Pro 4Gemini-3.1 Pro 5
Sonnet-4.6 1Sonnet-4.6 2Sonnet-4.6 3Sonnet-4.6 4Sonnet-4.6 5
Sonnet-4.6 1Sonnet-4.6 2Sonnet-4.6 3Sonnet-4.6 4Sonnet-4.6 5
Opus-4.6 1Opus-4.6 2Opus-4.6 3Opus-4.6 4Opus-4.6 5
GLM-5 1GLM-5 2GLM-5 3GLM-5 4GLM-5 5
Kimi-K2.5 1Kimi-K2.5 2Kimi-K2.5 3Kimi-K2.5 4Kimi-K2.5 5
Qwen-3.5 1Qwen-3.5 2Qwen-3.5 3Qwen-3.5 4Qwen-3.5 5
Lovable 1Lovable 2Lovable 3Lovable 4Lovable 5
V0-Max 1V0-Max 2V0-Max 3V0-Max 4V0-Max 5