Apple Intelligence powered. Blazing-fast Apple SpeechAnalyzer + on-device AI formatting.
No API keys. Fully offline. Your data never leaves your device.
New: real-time subtitle translation for audio from any video.
One click from your menu bar. Every feature on a clean, intuitive tab.
Apple’s new entry-level Mac — the MacBook Neo — is “Built for Apple Intelligence.”
RocketWhisper v2.2.5 is tuned to run instantly on the Neo’s 8GB RAM / 256GB SSD
with zero model downloads and zero API keys.
RocketWhisper provides advanced features not available in macOS built-in dictation.
Uncompromising features designed for professional demands.
Real-time floating subtitles for any audio playing on your Mac — meetings, videos, podcasts, and more. Your Mac listens to system audio and displays translated captions in a Netflix-style overlay — powered by Apple SpeechAnalyzer + Translation. Fully on-device, no API keys, no cloud. Watch English talks with Japanese subtitles, follow Chinese news in English, and more across 10+ languages.
Note: Live Translation requires macOS 26 Tahoe or later (not available on macOS 14 Sonoma / 15 Sequoia). All other features work on macOS 14+.
Complete English UI, voice commands, voice search, AI commands, and presets. Say “new line,” “new paragraph,” “Search for ...” — English-tuned prompts and auto-switching based on your system language. Zero impact on Japanese users.
Native Apple speech recognition on macOS 26. No model download needed, 2x faster than WhisperKit. Switch with one click in Settings. WhisperKit still available on macOS 14-15.
On-device ~3B Foundation Models on macOS 26. No API keys, no internet — AI text formatting works completely offline. Best for grammar fixes and light formatting. Cloud APIs also available for advanced tasks.
High-accuracy recognition powered by Neural Engine and CoreML. Choose from 4 WhisperKit models + Apple SpeechAnalyzer.
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 6 providers: Apple Intelligence, OpenAI, Claude, Gemini, Groq, and Local LLM. Apple Intelligence requires no API key. 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.
v2.2.5 | macOS 14.0 Sonoma or later | Apple Silicon & Intel | Live Translation requires macOS 26+
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, RocketWhisper is optimized for the MacBook Neo. Since v2.1.0, the default speech engine on macOS 26+ is Apple's SpeechAnalyzer (OS-built-in), so the WhisperKit model download (several hundred MB to GB) is no longer required. Even with 8GB RAM / 256GB SSD, the Neo can run AI voice input right after install — without eating disk space or API keys. AI text formatting via Foundation Models also runs entirely on-device; no cloud traffic.
Added in v2.2.1, Live Translation listens to any audio playing on your Mac (meetings, videos, podcasts, and more) through Apple SpeechAnalyzer, translates it with Apple Translation, and shows Netflix-style floating subtitles on top of your desktop. Zero cloud traffic, no API keys, fully on-device — across 10+ languages. Watch English talks with Japanese subtitles, follow Chinese news in English, and so on. Drag the overlay to reposition, and fine-tune the number of subtitle lines and source-text visibility. Requires macOS 26 or later.
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.