Auday

The best AI recording hardware?
You may already own it!
Turn your Apple Watch⌚ into an all-day AI recorder.
🪄Website: Auday on the AppStore!

[Auday @auday_ai]

Appreciate you trying Auday and laying out the workflow you'd like! We're working on a higher-accuracy local transcription option with speaker recognition for the next version, while keeping the lightweight model. Stronger on-device transcription is very achievable; our current choice balances accuracy, speed and memory use across different iPhones. Selectable noise reduction is also planned, though separating speakers doesn't necessarily mean removing TV audio.

For Hermes or Obsidian workflows, you can manually export audio and transcripts today. We haven't announced a direct integration with either. Auday can hold conversations alongside personal health, activity and location context, so we're careful about opening up access. Core records stay on your devices, without an Auday account system or content-relay server. We're exploring a private Agent layer that could share only the necessary context with outside assistants under your control; that's a future direction.

We've also noted your request for scheduled recording start and stop. Thanks for explaining what would make Auday fit your day better!

[Auday @auday_ai]

We appreciate you flagging both issues. If you mean speech-to-text accuracy, changing the connected AI model won't change it: transcription runs locally on your iPhone. The connected AI uses that transcript and context for summaries and Chat, so its output can vary by model. Higher-accuracy transcription technology is already mature, and adding a stronger model is well within our capabilities. Our current lightweight model balances accuracy with speed and memory use across different iPhone generations. For the next update, we're working on an optional higher-accuracy local model while keeping the lightweight option, and planning selectable noise reduction. Original audio stays on your devices; optional AI sends relevant text and context directly to your configured provider.

I'm sorry the menus and selection/copy controls are switching to Chinese despite your Japanese selection. Could you share your Auday version and a screenshot of just the affected controls, with personal records and any API keys hidden? That will help us identify the exact screen and investigate the language behavior.

[Auday @auday_ai]

Glad you're enjoying Auday! Bringing conversations together with your activity and body signals is exactly the context we want to make useful when looking back. For models beyond the presets, Claude's provider settings include a Custom model option where you can enter an Anthropic API model ID, then use Check Connection & Save. Whether a model works depends on your API account and compatibility; it isn't guaranteed simply by entering its name. We've noted your request as we improve model support.

[Auday @auday_ai]

Appreciate your interest! Auday doesn't currently have a web version. You can use Claude inside Auday's Chat with your own Anthropic API key to ask questions about your recorded conversations. Connecting a Claude account/subscription or letting the Claude app directly access your Auday archive isn't supported; you can manually export transcripts to use in your own workflow.

Auday can hold conversations alongside health, activity and location context, so we've kept core recording and processing on your devices, with no Auday account system or content relay server. When you use optional AI, relevant text and context go directly to the provider you configure; original audio stays on your devices. We're also exploring a private Auday Agent that could share only the context needed for a task with outside assistants, with your permission. Those connections are a future direction, not available integrations today.

[Auday @auday_ai]

The best AI recording hardware?
You may already own it.

Introducing Auday—now live on Product Hunt.
Turn your Apple Watch into your all-day AI recorder.

Beyond voice, Auday combines health, real-time stress, location, and other signals to understand your everyday life—not just answer your questions.

Record on your wrist. Revisit your day with transcripts, timelines, highlights, reflection, and AI chat.

Almost everything runs locally on your devices. Bring your own API key for AI. We don't even have a backend server.

App Store launch offer: half price. Just $9.99 for a one-time purchase. No subscription.

We'd love your support and feedback on Product Hunt. Take a look, join the conversation, and tell us what you'd want your watch to remember.

Product Hunt: https://t.co/SfMqMH9FaI
App Store: https://t.co/VXAoQquQet
Website: https://t.co/7h4w2yc8Mj

[Auday @auday_ai]

Sorry the recordings aren't reaching your iPhone. Auday transfers them directly from your Watch to its paired iPhone through Apple's WatchConnectivity, without an Auday server in between. With the devices close together and Auday open on both, please try "Manually sync now" once on your iPhone and see whether the "Awaiting sync" duration changes; keep the pending recordings in place rather than reinstalling. If it stays stuck, could you share your Watch and iPhone models, watchOS/iOS and Auday versions, and the sync status shown?

[Auday @auday_ai]

We appreciate you explaining where you're getting stuck, and the suggestion for a Japanese setup and walkthrough video. Some interface controls remain in English: we've carefully tuned the English typography, spacing and short button labels, and other languages need further layout work to preserve that clarity and visual balance. We understand that this still makes getting started harder for you. Japanese transcription runs locally on your iPhone, and in version 1.0.1 you can choose Japanese in Settings → AI Primary Language for summaries, Highlights, daily Reflections and Chat. That setting changes AI content, not the settings interface. We've noted your request for clearer Japanese guidance and a video walkthrough as we improve the experience.

[Auday @auday_ai]

Auday 1.0.1 is now live!

This update adds Japanese and Korean support for AI-generated content, including summaries, Highlights, daily Reflections and Chat replies. You can switch languages in Settings → AI Primary Language.

It also fixes the silent-recording issue affecting some Apple Watch Ultra users, improves transfer reliability between Apple Watch and iPhone, and brings a major overhaul of local storage for smoother loading and browsing as your recording history grows.

On launch day, Auday reached #1 in the App Store’s paid Lifestyle charts in multiple countries. The response has far exceeded our expectations, and every download, message and suggestion has been a huge encouragement. Behind Auday is a solo developer, working late to collect your feedback, investigate issues and keep improving the app. Thank you for your support and patience.

We also want to explain the choices behind transcription. To support a wider range of iPhones while keeping resource use low and minimizing slowdowns, our current on-device speech recognition model prioritizes speed and efficiency. In tests on iPhone 17 Pro, several hours of audio often took just a few seconds to transcribe. Actual performance varies with the device and recording. That speed comes with some accuracy trade-offs. Auday AI uses surrounding context when interpreting transcripts and generating content to help identify and work through recognition errors, reducing their impact on summaries, analysis and conversations.

For the next update, we plan to introduce an optional speech recognition model with higher accuracy and slightly higher resource requirements, alongside the current lightweight model. You’ll be able to switch between them and choose the balance of speed and accuracy that best suits your iPhone and your needs. We’ll also continue adding support for more languages.

To thank everyone for the support, we’re extending our 50% launch discount for one more week. Buy once, with no Auday subscription.

AppStore: https://t.co/VXAoQquioV

Thank you for being part of Auday’s beginning. We’ll keep listening and making it better.

[Auday @auday_ai]

@kedama_room Love seeing Auday become part of your workday! Having the recording already on your wrist means one less thing to remember when a useful conversation comes up. Really appreciate you sharing how you use the audio with your other tools.

[Auday @auday_ai]

Thanks for sharing how you're using Auday overnight! Auday doesn't analyze health or assess sleep from snoring recordings. Sleep information isn't displayed separately in the app; it is used as context for the AI, alongside the text from your recorded conversations, to help it understand your day more fully.

[Auday @auday_ai]

Thank you for giving Auday a try, Roberto, and I'm sorry Spanish wasn't available when you bought it. Our community is growing quickly, and we're gathering language requests from users around the world, including Spanish. We'll keep adding support for more languages in future updates, and we'd love for you to enjoy Auday in your own language too. We appreciate your patience and support.

[Auday @auday_ai]

We appreciate you spending a full day with Auday, and it’s good to hear the everyday usability is working for you. Japanese transcription accuracy is a priority: higher-accuracy speech recognition is already mature technology, and adding a stronger model is very achievable for us. Our current lightweight model balances accuracy with speed and memory use across different generations of iPhone; for the next update, we’re working on a higher-accuracy local option while keeping the lightweight model, with selectable noise-reduction levels also planned. That will give you a choice based on your phone and recording needs, while keeping transcription on-device and original audio on your devices.

[Auday @auday_ai]

@shin00ryu Thanks for flagging this! Is Japanese missing from the transcript, the AI-generated content, or the app’s settings screen? That will help us give you the right guidance.

[Auday @auday_ai]

Japanese transcription is already supported and runs locally on your iPhone. Version 1.0.1 added Japanese output for AI summaries, Highlights, daily Reflections and Chat. We’re sorry that distinction wasn’t clear, and we understand your concern about the recognition quality you’re seeing.

You’re right that using the same Watch can produce different transcription results: Auday’s speech-to-text model runs on the iPhone, separately from the AI provider used for recaps. Higher-accuracy transcription technology is mature, and adding a stronger model is very achievable for us. Our current lightweight model balances accuracy with speed and memory use across different generations of iPhone; we’re working on an optional higher-accuracy local model for the next update, keeping the lightweight option, with selectable noise-reduction levels also planned.

The recap AI can use context to help interpret recognition errors, but it cannot correct every error or reliably recover missing speech. So your point about transcript quality affecting recaps is valid, and improving transcription is a priority.

[Auday @auday_ai]

Thank you for sharing the details. We’ve noted your Apple Watch Series 12, watchOS 27.0.1 and Auday 1.0.1, together with your observation that notification vibrations return when recording stops and that Voice Memos behaves the same way. That gives us a useful comparison with the other reports as we investigate.

[Auday @auday_ai]

We’re glad keeping the written record matters to you, and appreciate the comparison and the request for a choice of models. Higher-accuracy on-device transcription is already a mature technology, so adding a stronger model is very achievable for us; the current lightweight model was chosen to balance accuracy with speed and memory use across different generations of iPhone. We’re working on an optional higher-accuracy local model for the next update while retaining the lightweight option, with selectable noise-reduction levels also planned. That will let you choose the balance that suits your phone and recording needs, while keeping transcription local and original audio on your devices. Thank you for trying Auday and helping us improve it!

[Auday @auday_ai]

We appreciate you trying Auday and sharing this. Connecting a different AI provider won’t change the speech-to-text model: transcription runs locally on your iPhone, while the connected AI uses the transcript and context for summaries, reflections and Chat. It can help interpret recognition errors, but doesn’t rewrite the original transcript or recover everything that was missed.

Higher-accuracy transcription technology is already mature, and adding a stronger model is very achievable for us. The current lightweight model balances accuracy with memory use, speed and smooth operation across different generations of iPhone. For the next update, we’re working on an optional higher-accuracy local model while keeping the lightweight option, and planning selectable noise-reduction levels. This keeps transcription on-device and the original audio on your devices; optional AI sends the relevant text and context directly to the provider you configure.

For Japanese AI content, version 1.0.1 supports summaries, Highlights, daily Reflections and Chat in Japanese via Settings → AI Primary Language. Some interface controls remain in English. We’ve carefully tuned the English typography and layout, using short, straightforward button labels; other languages need further layout work to preserve that balance. That’s why we’ve focused language support on the content you read and use most, while keeping these simpler controls in English for now. Thank you for the feedback on both areas!

[Auday @auday_ai]

Really appreciate your support over these first three days! Keeping your recordings and notes in your own storage makes sense. Today, Auday's export workflow is manual: after a day has ended, use the top-right export option in Daily Reflection for that day's recorded audio. In Days, open an hour's details to export its audio, transcript or text such as Highlights, then save the exported files to your preferred storage.

We're planning encrypted bulk export and import to make backing up and moving your records easier. Your request to keep audio and summaries together in personal storage is useful feedback for that work; we haven't announced automatic Google Drive syncing.

Because Auday can contain conversations alongside health, activity and location context, privacy is central to these choices. Core records and processing stay on your devices, without an Auday account system or content-relay server. We're also exploring a private Auday Agent between your personal records and outside assistants, so you can choose what context to share. That is a future direction, while manual export is available now.

[Auday @auday_ai]

The screenshots are very helpful, thank you. We've noted your Apple Watch Ultra 2, watchOS 27.0 (24R364) and Auday 1.0.1 (22), along with your confirmation that notification vibrations return when recording stops. This gives us a clearer setup to compare with the other reports. We appreciate you helping us investigate.

[Auday @auday_ai]

We're glad you're enjoying Auday, and sorry the notification issue is getting in the way. When you say notifications no longer ring, do you mean the sound, the vibration, or both, and does it return when you stop recording? Please also share your Watch model, watchOS and Auday versions. We've received reports about notification vibrations during recording, but would like to understand exactly what you're experiencing before drawing a conclusion.

[Auday @auday_ai]

You're not the only person to report this. Another user also found that notification vibrations stop during recording and return afterward, including in Voice Memos. Thank you for checking both apps; that comparison is helpful, but we haven't confirmed whether this is expected watchOS behavior or another issue. Could you share your Apple Watch model, watchOS version and Auday version so we can compare the reports?