3x Faster Than Typing
Speak 150+ words per minute vs 40 wpm typing. Finish tasks in a third of the time.

Document APIs and architecture decisions by voice
Read this example aloud, or say something of your own.
Your voice. Right where you work.

Place your cursor in any app, then hold the Fn key.

Say what you want to write. Ottex follows your saved writing rules.

Your text appears right where your cursor is.
Concrete benefits with real-world impact
Speak 150+ words per minute vs 40 wpm typing. Finish tasks in a third of the time.

Speaking naturally gives AI agents more context than typing. Describe your intent, explain edge cases, mention file names—your voice carries nuance that typing shortcuts.

Cloud AI models excel at technical jargon, code terminology, and specialized vocabulary.

Add names, technical terms, and jargon. Ottex transcribes them accurately every time.

Transform text as you speak: 'Ottex start fix grammar Ottex end'. Edit, improve, translate—all by voice.

Say 'new paragraph', 'open quote', 'em dash', 'ellipsis'. Full formatting control by voice.

Dictate prompts to ChatGPT, Claude, Perplexity—anywhere you type. Better prompts, better answers.

Say 'scratch that' to delete mistakes, 'actually' to rephrase. Fix errors without stopping your flow or touching the keyboard.

Works in VS Code, Cursor, JetBrains, Xcode—any editor. Dictate prompts to AI coding assistants.

Ottex detects which app you're in and adapts. Coding mode in Cursor, casual tone in Slack, professional in Gmail—automatic context switching.

Optionally let AI see your screen for smarter responses. Reply to emails with full context, answer messages knowing the conversation history.

Define custom text replacements and shortcuts. Say 'work signature' to expand your full email signature, or 'my address' for your contact info.

Start recording with Option+D, use Push-to-Talk, or cancel with Esc. All shortcuts are fully configurable.

System-wide on macOS—Ottex works wherever you can type. No app-specific integrations needed.

Automatically removes filler words like 'um', 'uh', 'like', 'so' from your transcription. Get clean, professional text without verbal hesitations.

Dictate technical documentation, READMEs, or API docs. Speaking lets you explain context, edge cases, and examples naturally—better docs with less effort.
Works with
Read this example aloud, or say something of your own.
Dictate prompts to ChatGPT, Claude, Perplexity, or any AI chatbot. Speaking naturally lets you give more context—better context means better results.
Read this example aloud, or say something of your own.
Dictate Jira tickets, Linear issues, or Asana tasks. Speak the context, acceptance criteria, and details—then move on.
Read this example aloud, or say something of your own.
Dictate detailed prompts to AI coding assistants in Cursor, Copilot, or Claude Code. Explain what you need naturally without losing your train of thought.
Read this example aloud, or say something of your own.
Reply to Slack messages 3x faster. Dictate casual updates, detailed explanations, or quick acknowledgments without switching context.
Read this example aloud, or say something of your own.
Dictate meeting notes in real-time or right after. Capture action items, decisions, and key points while they're fresh in your mind.
Works with
Read this example aloud, or say something of your own.
Speak ideas the moment they hit you. Use Ottex anywhere to capture thoughts, then refine them later.
Works with
Read this example aloud, or say something of your own.
Dictate email responses with the right tone. Use context awareness to see the full thread, then speak your reply naturally.
Read this example aloud, or say something of your own.
Yes. Cloud models like Gemini 3 Flash are trained on technical documentation. They handle 'REST API,' 'PostgreSQL,' 'GraphQL resolver,' 'Redis cache invalidation,' and similar terms accurately. Add project-specific terms (service names, internal tools) to your custom dictionary.
Absolutely. Ottex works in any IDE or text editor. Dictate JSDoc comments, Python docstrings, Go doc comments, or Rust doc comments. Use precision typing commands like 'new line' and 'open curly brace' for code formatting.
Ottex works in any browser text field, including GitHub PR descriptions and review comments. Dictate detailed explanations of your changes, respond to review feedback, or explain architecture decisions in PR discussions.
Yes. With BYOK, your audio goes directly to your API provider (Google, OpenAI, etc.)—Ottex never sees your data. For maximum privacy, use local models for 100% offline processing. No screen capture, ever.
Yes. Speaking lets you explain complex debugging scenarios naturally: stack traces, expected vs actual behavior, what you've tried. More context means better debugging suggestions from AI.
No. Ottex uses less than 2% CPU because it's native Swift. Cloud processing happens via API, so your build times, test suites, and Docker containers won't be affected.
Download free. Use local models immediately, or add your API key for cloud quality. Start dictating API docs in minutes.
Try for freeNo credit card required.