Everything DuckType can do
100+ languages, CJK romanization, regional spelling corrections, AI skill chaining, and a lot more.
Transcription
Transcribe meetings, lectures, interviews, and more
Works offline with local models, or connect to the cloud for even more accuracy. Then AI skills fix grammar, translate, summarize, or do anything you describe in a prompt.
100+ languages
From English and Spanish to Japanese, Arabic, and Hindi. Language support varies by provider, with up to 100 languages on some engines.
Bring your own key
Connect your own OpenAI, Groq, Deepgram, or ElevenLabs account to unlock specialist models like Deepgram Nova 3 Medical and ElevenLabs Scribe v2. No markup on API costs. Your keys are stored locally, never sent to our servers.
Or let us handle it
DuckType Cloud starts at 200,000 words/month, with a 600,000-word Pro plan for heavier use and automatic provider fallback. If cloud providers are unreachable, DuckType switches to local models automatically. No API keys to manage.
Cloud providers
DuckType Cloud
Managed
OpenAI
Whisper
Groq
Whisper
Deepgram
Nova 3, Nova 3 Medical
Mistral
Voxtral Mini, Voxtral Small
Cloudflare
Workers AI
Baseten
Bring your own model
ElevenLabs
Scribe v2
Local models (offline)
Whisper
100 languages, multiple sizes
Parakeet TDT
English, high accuracy
SenseVoice
Chinese, Japanese, Korean, English, Cantonese
Recording Modes
Start recording your way
From push-to-talk for quick edits to always-on auto mode for continuous dictation. Every mode works globally, even when DuckType is minimized.
Push-to-talk
Hold a key to record, release to transcribe. The classic mode for precise control.
Click to record
Toggle recording with a click or keyboard shortcut. Good for longer dictation sessions.
Double-tap
Double-tap a modifier key to start recording. Quick activation without reaching for a shortcut.
Fn key hold
Hold the Fn key to record. Native feel, no custom shortcut needed.
Auto mode
Always-on listening with voice activity detection. Sentences are segmented by silence gaps. The microphone automatically switches to your preferred device when it becomes available.
Instant recording
Reuses the microphone stream between recordings so there is near-zero activation latency. No Bluetooth warm-up delay. Recording starts the instant you speak.
Meetings
Record, transcribe, and summarize meetings
Capture any conversation with live transcription and AI-generated summaries. Works with video calls, in-person meetings, or any audio on your machine.
System audio capture
Record audio from Zoom, Google Meet, Teams, or any app playing sound. Capture your microphone, system audio, or both at the same time. No extra software needed.
Live transcription
Speech is transcribed in real time as the meeting progresses. Voice activity detection segments speech automatically so you can follow along as it happens.
AI summaries
When the meeting ends, generate a summary with key decisions, action items, and open questions. Uses your configured LLM provider. Can run automatically or on demand.
Meeting notes
Write and edit markdown notes alongside the transcript. Notes are saved locally as plain files you can open in any editor.
Import recordings
Drop an audio or video file to transcribe and summarize an existing recording. Pause and resume multi-session recordings without losing context.
Search and organize
Full-text search across all meetings and transcripts. Organize with folders and browse your full meeting history.
AI Processing
Transform text after transcription
AI skills run on your transcription to fix grammar, translate, summarize, or do anything you can describe in a prompt.
Custom AI skills
Create skills with custom prompts. Fix grammar, translate to another language, summarize meeting notes, rewrite for tone, or anything else. Skills can run automatically on every transcription or be triggered manually.
Skill chaining
Chain multiple skills in sequence. The output of one becomes the input of the next. Transcribe, then translate, then format as bullet points, all in one pass.
7+ LLM providers
Skills work with your choice of language model. Use cloud APIs or run locally with Ollama for fully offline AI processing.
Import audio & video
Drag and drop, paste, or pick any audio or video file. MP4, MOV, MP3, WAV, FLAC, OGG, WebM, and 25+ more formats. DuckType extracts the audio and converts it to text. Skills run on the result just like live dictation.
Language Intelligence
Beyond transcription accuracy
DuckType understands regional spelling variants, romanizes CJK scripts, and learns your vocabulary. No other dictation app does this.
CJK Romanization
Dictate in Japanese, Chinese, or Korean and get romanized Latin-script output alongside the original text. Useful for language learners, subtitlers, and anyone working across writing systems.
東京
tōkyō
Lindera tokenizer for accurate kanji readings
你好世界
nǐ hǎo shì jiè
Character-level pinyin with tone marks
한국
han gug
Hangul decomposition using standard system
Regional spelling corrections
Most transcription engines output American English or Brazilian Portuguese by default. DuckType automatically corrects spelling to match your regional variant.
British English
European Portuguese
Swiss German
Dictionary & shortcuts
Dictionary
Create multiple dictionary lists for different contexts. Technical terms, product names, medical vocabulary. Toggle lists on and off as needed.
Text replacements
Define shortcuts that expand into longer text. Type abbreviations, email signatures, code snippets, or frequently used phrases.
1,900+ emoji and shortcuts
Built-in Unicode emoji library and text shortcuts. Say a trigger word and DuckType inserts the emoji or expanded text for you.
Productivity
Built for people who dictate all day
Global shortcuts, deep customization, and a progression system that keeps you motivated.
Paste at cursor
Transcribed text is pasted directly where your cursor is. Works in any app: text editors, browsers, chat windows, terminals. Runs alongside other recording apps without conflict.
Statistics & levels
Track words per minute, daily word counts, and dictation streaks. Hit milestones and level up your duck from Duckling to Admiral.
Skill presets
Group multiple skills into reusable presets. Switch between workflows with a single shortcut. One for emails, one for code comments, one for meeting notes.
CLI
Transcribe audio and video files from your terminal. Pipe output into other tools, run batch jobs, or integrate DuckType into shell scripts and automation workflows.
Claude Code skill
Transcribe audio and video files directly inside Claude Code. Ask questions about recordings, get summaries, or search transcriptions without switching context.
Deep customization
Custom AI prompts, configurable silence thresholds, per-app recording profiles, and fine-grained control over every setting. Tune DuckType to match how you work.
Privacy
Your data stays yours
DuckType is designed so your data never goes anywhere you didn't choose. No surveillance, no telemetry by default, no data harvesting.
No screen reading
DuckType never reads your accessibility tree, captures window contents, or inspects what's on your screen. Accessibility access is optional and only used for cursor positioning.
No URL logging
DuckType does not track which apps you use, which websites you visit, or what you're doing when you dictate. Zero behavioral data is collected.
Automatic offline fallback
DuckType automatically falls back to local models when your internet is down or a cloud provider fails. You can also run fully offline by choice. Nothing leaves your device.
Independent, not VC-backed
DuckType is independently built. No investors pushing for growth metrics or data collection. Your subscription pays for development. That's it.
Technical
Built with Rust, not Electron
DuckType uses Tauri and Rust for native performance with a fraction of the resource usage of Electron-based alternatives.
Tauri + Rust
Native Rust backend with a lightweight webview frontend. No bundled Chromium. Low memory and CPU footprint.
Platform-sized downloads
Around 35 MB on macOS. Around 80 MB on Windows because it includes the ffmpeg media sidecar. Electron-based competitors are around 238 MB.
Never lose your work
Every transcription is saved locally in SQLite. Search, edit, and re-run skills on your full history. If a transcription fails or the app crashes mid-recording, your audio is preserved and automatically recovered on next launch.
macOS and Windows
Supports macOS 11 Big Sur and newer, plus Windows 10 or newer. Linux and mobile support are planned.
Try DuckType
Download for macOS 11 Big Sur and newer, or Windows 10 or newer. Unlimited words with local models or your own API key. No account or credit card needed.
Download DuckType