What is Superwhisper?
Superwhisper is a macOS and iPhone app that converts spoken words into text using AI. It works in any app or website where typing is possible — Slack, Gmail, Notion, coding environments, and more. It supports over 100 languages and dialects and processes audio entirely on-device, with no internet connection required.
Features & Benefits
- On-device transcription – Process voice to text locally without an internet connection or Wi-Fi.
- Multilanguage support – Transcribe speech in 100+ languages and dialects, with translation to English available.
- File transcription – Upload audio or video files and receive accurate text transcripts.
- Meeting assistant – Record meetings and generate automatic notes without manual effort.
- Predefined modes – Apply preset tone, structure, and formatting profiles — including Voice, Message, Email, Legal, Formal, Casual, and Chat — so output is ready to use immediately.
- Custom Mode – Define formatting rules, structure preferences, and custom prompts for specific tasks. Choose from AI models including GPT, Claude, or Llama to match speed and accuracy requirements.
- Super Mode – AI-enhanced mode that reads the current screen context to produce more relevant output.
- Custom vocabulary – Add names, abbreviations, and specialized terms once; Superwhisper applies them consistently in all future transcriptions.
- Push to talk – Hold a key to record, release to transcribe. No additional setup per session.
- Custom shortcuts – Set keyboard shortcuts to launch, dictate, and control the app.
- Clipboard integration – Paste edited transcripts directly into the active app without manual copy-paste steps.
- Agentic workflow support – Use voice input to direct agentic coding tools like Cursor, Claude Code, Codex, and Amp without touching the keyboard.
Real-World Applications
Writers, journalists, and content creators who need to produce large volumes of text quickly may find a voice to text tool like Superwhisper significantly faster than typing. A blogger drafting a 1,000-word article can speak a rough draft in minutes, with Superwhisper applying a predefined mode to match the right tone and structure before the text even lands on screen. Legal and medical professionals who work with specialized terminology can add field-specific vocabulary once and rely on consistent, accurate output across every session.
Professionals in meetings or on calls can use the meeting assistant feature to capture notes automatically, freeing attention for the conversation itself. Rather than reconstructing what was said afterward, users get a structured summary they can act on immediately. This is particularly useful for remote teams using tools like Slack or Notion, where Superwhisper pastes transcribed text directly into the active window.
Developers working with agentic coding environments may get more out of AI coding tools by using voice to deliver detailed context. Speaking through a feature request or bug description gives tools like Cursor or Claude Code more to work with than a short typed prompt. Users who rely on multiple agents simultaneously can direct them faster by voice than by keyboard, without switching context between windows.
For users who work in multiple languages — whether translating communications, supporting international clients, or writing in a non-native language — Superwhisper’s support for 100+ languages and built-in English translation reduces friction in multilingual workflows. The offline capability makes it practical in low-connectivity environments like flights, fieldwork, or areas with unreliable internet.
