Features - AI Voice Input & Text Polishing

Explore all OpenTypeless features: multi-provider speech-to-text, AI text polishing, 21 language support, and customizable hotkeys for desktop voice input

Bring Your Own Providers

Configure your own STT and AI polish providers with your API keys. 6 STT + 11 LLM providers supported. Switch anytime without losing your settings — no vendor lock-in.

OpenTypeless supports Deepgram, OpenAI Whisper, Groq Whisper, GLM-4-Voice, AssemblyAI, and SiliconFlow as speech-to-text providers. Each provider has different strengths: Deepgram offers the lowest latency at around 300ms, Groq Whisper provides the best free tier, and OpenAI Whisper delivers the highest accuracy for complex audio. You can switch between providers at any time from the settings panel without re-configuring your workflow.

AI-Powered Text Polishing

Connect to 11 LLM providers to automatically refine your transcriptions. Fix grammar, improve formatting, adjust tone — all in real-time as you speak.

Supported LLM providers include OpenAI GPT, DeepSeek, Google Gemini, Anthropic Claude, Moonshot, Qwen, Zhipu GLM, Yi, Ollama (local), LM Studio (local), and Groq. The polishing step runs after transcription to fix punctuation, remove filler words, correct grammar, and format your text for professional use. You can customize the polish prompt to match your writing style or add translation instructions.

99 Languages with Auto-Detection

Speak in any of 99 supported languages. OpenTypeless auto-detects your language or lets you set a preferred one. Powered by Whisper — perfect for multilingual workflows.

Language support is powered by OpenAI Whisper, which covers 99 languages including English, Chinese, Japanese, Korean, Spanish, French, German, Arabic, Hindi, and many more. Auto-detection works by analyzing the first few seconds of speech to identify the language. For multilingual users who switch between languages frequently, you can set a preferred language to skip detection and reduce latency.

ENEnglish
ZH中文
JA日本語
KO한국어
ESEspañol
FRFrançais
DEDeutsch
PTPortuguês
RUРусский
+13 more

Global Hotkey — Works Everywhere

One keyboard shortcut activates voice input from any application. No window switching, no clicking. Just press, speak, and your text appears at the cursor.

The global hotkey works system-wide across all desktop applications — text editors, browsers, chat apps, email clients, IDEs, and more. On Windows, macOS, and Linux, you can customize the shortcut key combination in the settings. The hotkey toggles recording on and off, so you press once to start speaking and press again to stop. Your transcribed and polished text is automatically pasted at the cursor position.

Alt
Space
Hold to Talk
Toggle

Custom Dictionary

Add technical terms, product names, and specialized vocabulary. The AI learns your jargon and gets it right every time.

The custom dictionary is especially useful for developers, medical professionals, legal experts, and anyone who works with specialized terminology. Add company names, technical acronyms, product names, or domain-specific jargon. The dictionary entries are sent to the LLM as context during the polishing step, ensuring that terms like 'Kubernetes', 'PostgreSQL', or your company's product names are always spelled correctly.

WordPronunciation
+ Add
Kuberneteskoo-ber-NEH-teez
PostgreSQLpost-GRES-kew-ell
IstioIS-tee-oh

Privacy First

Your API keys stay on your machine. Audio is sent directly to your chosen provider — we never see or store your data. Fully open source for transparency.

OpenTypeless is built with a privacy-first architecture. The desktop app runs locally on your machine using Tauri (Rust + React). Your API keys are stored in a local encrypted configuration file and never transmitted to our servers. Audio data flows directly from your microphone to the STT provider you selected. The entire codebase is open source under the MIT License, so you can audit every line of code yourself.

STT Keysk-****...7x2f
LLM Keysk-****...m9kp
💻Stored locally
🔗Direct to provider
🔒We never see your data

Frequently Asked Questions

Common questions about OpenTypeless features and capabilities

Do I need an internet connection to use OpenTypeless?

You need an internet connection for cloud-based STT and LLM providers. However, if you use Ollama or LM Studio as your LLM provider and a local Whisper model, you can run OpenTypeless completely offline. The desktop app itself runs locally and does not depend on our servers.

Which STT provider should I choose?

It depends on your priorities. Deepgram offers the fastest response times (around 300ms) and is great for real-time use. Groq Whisper provides a generous free tier and good accuracy. OpenAI Whisper has the highest accuracy for noisy environments. AssemblyAI excels at speaker diarization. You can try each provider and switch anytime without losing your settings.

Can I use OpenTypeless for translation?

Yes. You can speak in one language and have the AI polish step translate your text into another language. For example, speak in Chinese and get polished English output. Configure this by adding translation instructions to your custom polish prompt in the settings.

Is OpenTypeless really free?

The desktop app is completely free and open source under the MIT License. You bring your own API keys for STT and LLM providers, and many of these providers offer generous free tiers. Typical voice input usage costs less than $1 per month in API fees. The optional Pro plan ($4.99/month) provides pre-configured cloud STT and LLM so you do not need to manage your own API keys.

What platforms does OpenTypeless support?

OpenTypeless runs on Windows 10 or later (64-bit), macOS 12 Monterey or later, and Linux (Ubuntu 20.04+, Fedora 36+, Arch Linux). The app is built with Tauri, which provides native performance on all three platforms. You can also build from source if your distribution is not officially supported.