Whisperkit vs Conduck
Price, ratings, monetisation and update history for both apps, side by side ā with what reviewers say about each.
Whisperkit
Read full descriptionHide full description
Whisper turns speech into accurate text ā entirely on your device. Powered by Apple's Neural Engine and an open-source multilingual speech recognition model, Whisper transcribes audio recordings, voice memos, lectures, meetings, podcasts and videos directly on your iPhone. Nothing is uploaded. Nothing is tracked. No accounts. New: make music (beta). Describe a song ā style, mood, instruments, even lyrics ā and Whisper composes it on your device. KEY FEATURES ⢠On-device transcription ā your audio never leaves your iPhone ⢠Record audio directly in the app, import files from Files, iCloud or Photos, share audio from other apps, or paste a link to an audio or video file ⢠Supports many languages including English, Chinese (Simplified or Traditional), Spanish, French, German, Japanese, Korean, Russian, Portuguese, and Italian ā plus auto-detection ⢠Real-time progress with live segment-by-segment streaming ⢠Multiple model sizes ā pick speed or accuracy to match your needs ⢠Performance monitor shows CPU, memory and Neural Engine usage in real time ⢠Works offline once a model is downloaded ⢠Keeps working in the background while you use other apps ⢠Copy or share transcripts with one tap ⢠Beautiful, modern interface designed for iOS and iPadOS MAKE MUSIC (BETA) ⢠Describe the music and Whisper composes it on your device ⢠Add lyrics to have them sung, in many languages ⢠Fuller arrangement turns a short idea into a full band ⢠Every song is kept with its prompt and lyrics, to play, share or make again WHY ON-DEVICE MATTERS Most transcription apps send your audio to a server. Whisper does not. Your meetings, voice notes, interviews and personal recordings stay private because everything runs locally on your iPhone's Neural Engine. ⢠No accounts to create ⢠No subscriptions, no ads ⢠No analytics or tracking SDKs ⢠Works in airplane mode after the first model download ⢠Safe to use with confidential and sensitive recordings PERFECT FOR ⢠Journalists transcribing interviews ⢠Students capturing lectures ⢠Professionals transcribing meetings ⢠Podcasters generating show notes ⢠Writers dictating drafts ⢠Anyone who values privacy Whisper is open speech recognition done right ā fast, accurate, and yours alone.
Conduck
Read full descriptionHide full description
Conduck is the native Apple client for your self-hosted or BYO-key AI - in your pocket, in the car, and on your wrist. Connect your own AI server - OpenClaw, Hermes, or a compatible model server such as Pi or LM Aider - or bring an OpenRouter key for a hosted model and start in about a minute. Your keys, your AI. No Conduck account and no Conduck-operated intermediary server. Ask from anywhere ⢠iPhone & iPad: start a chat and type, or hold to talk ⢠Action Button, Shortcuts & Control Center: fire off a quick question without opening the app ⢠Apple Watch: ask straight from your wrist ⢠CarPlay: a hands-free voice conversation on the road ⢠Mac: a full desktop app and menu-bar companion, with a global hotkey and Screenshot & Ask Work: collect now, brief your AI later ⢠A private desk beside your chats. Save thoughts, voice notes, screenshots, links and files from the app, the share sheet, Shortcuts, the Mac menu bar, Apple Watch or CarPlay. A voice note is saved as words. ⢠Adding to Work sends nothing to your AI. Arrange materials on Home, or file them into projects with their own background notes. ⢠When you're ready, write the task, pick the materials and choose your AI. Review the exact message, then send. ⢠With a self-hosted agent and file exchange set up, files your AI returns join the project. ⢠With content sync on, the desk syncs through your private iCloud. Very large files stay on the device that captured them. Private by architecture, not by promise ⢠Conduck operates no intermediary server. No Conduck account, no analytics, no ads, no tracking. ⢠By default, your speech is turned into text by Apple on your own devices. Your voice never leaves them. ⢠Prefer a cloud transcription service? Your audio goes straight from your device to that provider with your own key. We're never in the middle. ⢠Your conversations stay on your device and sync through your own private iCloud. We can't read them. ⢠Your keys and tokens live in the Keychain, and every connection over the internet is HTTPS. A server on your own network can be reached without it if you choose, and Conduck says so on screen when you do. See what you actually use ⢠Settings shows a private record of request attempts and conversations over the last 7, 30 or 90 days, typed and spoken compared. ⢠Broken down by connection, device and requested model, with the token counts your AI reports, and reliability split into first-try deliveries, retries, cancellations and failures. ⢠Recorded on your devices and synced through your private iCloud. Never sent to us. Free plan and Conduck Pro ⢠Free: three active projects and three configured gateways in total across OpenClaw, Hermes and custom connections. Unconfigured options don't count, and OpenRouter never uses a slot. ⢠Pro: unlimited active projects and configured gateways on iPhone, iPad and Mac. ⢠Archive a project to free a slot. Above the free limits, choose which projects and gateways stay active; your materials, conversations and saved connection settings are kept. Conduck Pro is an optional monthly subscription: USD 29.99 in the US or EUR 29.99 in euro-area storefronts. Other storefront prices are shown in the app. Payment is charged to your Apple Account. It renews automatically unless canceled; manage it in your App Store subscription settings. AI and speech provider usage is billed separately by your chosen providers. Pro includes no model or voice credits. Terms: https://conduck.com/terms/ Privacy: https://conduck.com/privacy/ Open source The application source is available under Apache 2.0 at github.com/GigaDuckAI/conduck. Official App Store builds keep the Conduck identity and CarPlay; personal source builds use the Conduck Community identity without CarPlay. What you'll need Conduck is the interface, not the AI. You bring the AI and any key it needs; guided setup helps you connect. Conduck creates no account and hosts no model for you.
Screenshots
Verdict
The clearest difference is update cadence: Conduck at every 6 days against Whisperkit's every 2 months. Conduck also leads on device support (4 vs 2). Whisperkit's advantage is iOS requirement (18.5 vs 26.5). On price, ads and in-app purchases there is nothing between them.
Scored on Price Ā· Rating Ā· Positive reviews Ā· Number of ratings Ā· Update frequency Ā· Ads Ā· In-app purchases Ā· Monetization Ā· Best chart rank Ā· Devices Ā· Requires iOS
Both are free to download. Neither carries in-app purchases, so what you see is what you pay.
Whisperkit ships an update every 2 months, Conduck every 6 days. The most recent releases landed on October 12, 2026 and October 13, 2026 respectively.
| Parameter | Whisperkit | Conduck |
|---|---|---|
| Price | Free | Free |
| Update frequency | Every 2 months | Every 6 days ā better |
| Ads | No | No |
| In-app purchases | No | No |
| Devices | iPhone, iPad | iPhone, iPad, Mac, Apple Watch ā better |
| Requires iOS | 18.5 ā better | 26.5 |
| Further details ā not scored | ||
| Size | 24 MB | 71 MB |
| Age rating | 4+ | 17+ |
| Developer | chienchung Yu | GigaDuck OU |
In-app purchases
Whisperkit
No in-app purchases
Conduck
No in-app purchases








