Fully Offline AI Speech Recognition & Transcription — One-Time Purchase.
Harnesses the power of Neural Engine for high-accuracy voice-to-text. Your data never leaves your device.
RocketWhisper provides advanced features not available in macOS built-in dictation.
Uncompromising features designed for professional demands.
High-accuracy recognition powered by Neural Engine and CoreML. Choose from 4 models. Large V3 Turbo recommended.
All speech recognition is processed on-device. No internet required. Safely transcribe confidential information.
Default ⌥Space starts voice input from any app. Customizable. Right Option key also supported.
Register technical terms, company names, personal names, and acronyms to dramatically improve recognition. Not available in macOS built-in dictation.
Supports 5 providers: OpenAI, Claude, Gemini, Groq, and Local LLM. Grammar correction, business style, summarization, translation auto-processed.
Select text, press ⌃⇧Space, and give voice instructions. "Make formal", "Translate to English", "Summarize" - AI instantly edits selected text.
Pre-assign AI processing to dedicated shortcuts. Press shortcut → speak → press again for instant translation, summarization, grammar fix and more. 4 presets included, up to 20 custom instructions.
"Search for...", "What is...", "Look up..." - 10 voice command patterns instantly trigger Google search.
Launch apps or open URLs by voice. Say a keyword to instantly access your favorite tools.
Automatically apply different processing settings per app. Punctuation for editors, casual style for chat.
Edit text hands-free with voice commands like "new line", "paragraph", "delete". 7 built-in commands.
7-stage punctuation rules optimized for natural text output, automatically inserting commas, periods, and question marks.
Regex-supported correction rules for automatic misrecognition fixes. 27 hallucination filters built-in.
Mini equalizer-style waveform bar during recording. Draggable, always-on-top for visual confirmation.
Record while holding Right Option, auto-stop on release. Push-to-Talk style for intuitive voice input.
Push-to-Talk with Fn key (🌐). Double-tap to toggle continuous recording. Same feel as Wispr Flow or macOS Dictation.
Batch transcribe multiple audio files. Drag & drop to add, export as TXT, SRT, or VTT format.
Intelligent processing flow that automatically transforms recognized text into high-quality output.
Choose the optimal AI based on your use case, budget, and privacy requirements.
Select the optimal model based on speed and accuracy balance. All run on-device.
| Model | Size | Speed | Accuracy | Use Case |
|---|---|---|---|---|
| Small | 500 MB | ⚡⚡⚡⚡ | Real-time input | |
| Medium | 1.5 GB | ⚡⚡⚡ | Balanced | |
| Large V3 Turbo Recommended | 1.6 GB | ⚡⚡⚡ | High accuracy & speed | |
| Large V3 | 3.0 GB | ⚡⚡ | Maximum accuracy |
* For Japanese speech recognition, Large V3 Turbo or higher is recommended. Small/Medium may have reduced accuracy for kanji and katakana words.
7-day full trial. No credit card required.
v1.2.0 | macOS 14.0 Sonoma or later | Apple Silicon & Intel supported
All features are available for free during the trial period. After that, a one-time license purchase (Personal: ¥4,800 / ~$32) is required. No monthly subscription fees ever.
Yes, completely offline. All audio data is processed locally on your Mac and is never sent to any external server.
Powered by OpenAI Whisper’s latest model (large-v3-turbo), it delivers industry-leading accuracy. 73 hallucination countermeasures and custom vocabulary support ensure practical results.
Yes, runs natively on Apple Silicon (M1/M2/M3/M4) for optimal performance. Also works on Intel Macs.
Yes, both real-time and from recorded audio/video files via batch processing. AI processing can automatically summarize and reformat the text.
Yes, transcribes video files (MP4, MKV, AVI, MOV, WebM) and exports subtitles in SRT and VTT formats.