Staging environment. This is not the real DuckType. Go to duck-type.com.
DuckTypeDuckType

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.

OpenAI (GPT)Anthropic (Claude)Google (Gemini)GroqOpenRouterOllama (local)Any OpenAI-compatible

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

JapaneseRomaji

Lindera tokenizer for accurate kanji readings

你好世界

nǐ hǎo shì jiè

ChinesePinyin

Character-level pinyin with tone marks

한국

han gug

KoreanRevised Romanization

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

colorcolour
analyzeanalyse
centercentre

European Portuguese

bebêbebé
abdômenabdómen

Swiss German

straßestrasse

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