Auvi vs Apple Live Captions
Starting from the same privacy foundation — but going much further
Key difference in one sentence: Apple Live Captions is a free, private baseline that's already on your iPhone, but it's English-only, has no speaker identification, and text disappears the moment it appears; Auvi builds on the same on-device privacy approach while adding 40+ languages, colour-coded speaker identification, transcript history, and a range of accessibility features.
Apple Live Captions (available on iPhone from iOS 16) is the built-in captioning system from Apple. It's genuinely useful and genuinely private. For many people, it's a reasonable starting point. But users who rely on captions daily — particularly deaf and hard-of-hearing people — consistently find it insufficient.
Feature comparison
| Feature | Auvi | Apple Live Captions |
|---|---|---|
| Price | One-time purchase for Standard. 7-day free trial. | Free — included with iOS 16+. |
| Processing | Fully on-device. | Fully on-device. |
| Privacy | No data collected. App Store label verified. | Fully private. Apple does not collect caption data. |
| Languages supported | 40+ transcription languages on-device. | English (US and Canada) only. |
| Speaker identification | Yes — colour-coded speakers for multi-person conversations. | FaceTime calls only. No speaker identification for general use. |
| Accuracy | High accuracy engine with strong performance across accents and noise conditions. | Accuracy criticised by the deaf community as inconsistent, especially with accents, background noise, and multiple speakers. Improved in late 2025 but still behind dedicated apps. |
| Transcript persistence | Optional transcript saving to local storage (Plus add-on). Text stays until you clear it. | Text disappears. No saving, no history, no search. If you blink, you miss it. |
| Transcript history & search | Yes — searchable local history with Plus add-on. | No. |
| Real-time translation | 31 languages on-device with Translation add-on. | No translation. |
| Scam detection | Yes — 25 phone scam categories + 10 tourist scam categories. | No. |
| Sound awareness | Yes — identifies 15 environmental sounds with visual and haptic alerts. | No. (iOS has a separate Sound Recognition system, but it's not integrated into Live Captions.) |
| Font size control | In-app slider from 16–48pt, independent of system Dynamic Type settings. | Adjustable via system Accessibility settings. Less granular control. |
| Colour schemes | 5 schemes: system, light, dark, high-contrast, yellow-on-black. Colour-blind speaker palette toggle. | System appearance only. No high-contrast or yellow-on-black mode. |
| Apple Watch | Yes — live captions stream to Apple Watch. Start/stop from Watch. | No Watch support. |
| AirPlay / external display | Large-format captions on TV or projector via AirPlay or HDMI. | No. |
| Haptic feedback | Configurable haptics when new speech detected, keyword alerts, scam warnings. | No haptic feedback from Live Captions. |
| Screen stays on | Yes — prevents screen lock during active transcription. | No — screen can lock and you lose captions. |
| MDM / enterprise | Yes — Managed App Configuration for corporate deployment. | N/A — system feature, managed via standard iOS MDM. |
| Custom vocabulary | Yes — add custom words, domain vocabulary packs (Medical, Legal, Tech, etc.). | No. |
Why choose Auvi
- Text that stays on screen. Apple Live Captions text disappears as new text scrolls in. There's no way to scroll back to see what was said. In a fast-moving conversation, this is a serious limitation. Auvi keeps everything visible and scrollable.
- Speaker identification. If you're in a room with multiple speakers, Apple Live Captions shows a single undifferentiated stream of text. You cannot tell who said what. Auvi assigns each speaker a colour, transforming a stream of words into a readable conversation.
- More languages. Apple Live Captions works only in English (US and Canada). If you or anyone you speak with uses another language, Auvi supports 40+ languages on-device. With the Translation add-on, real-time translation into 31 languages.
- Better accuracy with accents and noise. Apple Live Captions has been consistently criticised by deaf community members for poor accuracy with non-standard accents and background noise. Auvi uses a more capable on-device speech recognition engine for higher accuracy in real-world conditions.
- Screen stays on. Apple Live Captions cannot prevent the screen from locking. In a long conversation, your screen dims and you miss captions. Auvi keeps the screen on for the duration of transcription.
- A complete accessibility tool. Auvi adds features Apple hasn't built: scam detection, sound awareness, customisable colour schemes for visual impairment, haptic alerts, external display support, and an Apple Watch companion app.
Why choose Apple Live Captions
- It's free. If you're an English speaker with modest captioning needs and privacy is your only concern, Apple Live Captions costs nothing. There's no download, no setup, no model download — it's already on your phone.
- System-wide integration. Apple Live Captions can caption any app on your phone — phone calls, video calls, media playback. It operates at the system level. Auvi is a standalone app focused on your microphone input.
- No setup required. Turn it on in Accessibility settings and it works immediately, with no model download or onboarding needed.
- FaceTime speaker identification. In FaceTime calls, Apple Live Captions does identify speakers. If FaceTime calls are your primary use case, this is built-in at no cost.
When to use both
Apple Live Captions and Auvi solve complementary problems. Apple Live Captions works across your entire phone at the system level — it can caption a video call, a podcast, or an app that's speaking to you. Auvi uses your microphone to caption in-person conversations around you.
Many users find it useful to have both: Apple Live Captions for media and system audio, Auvi for in-person conversations. They don't conflict.
Bottom line
Apple Live Captions is the right starting point for anyone who needs occasional captions and uses only English. It's private, free, and convenient.
For deaf and hard-of-hearing people who depend on captions daily, it falls short. Text disappearing, English-only, no speaker colours, no transcript history, inconsistent accuracy — these are not minor inconveniences. They matter every time someone speaks to you.
Auvi is designed for exactly this gap: the privacy and on-device architecture of Apple Live Captions, but with the accuracy, features, and depth that daily use actually demands.
Try Auvi free for 7 days
Full features including speaker identification, 40+ languages, and transcript history. No commitment. No data collected.
Download on the App Store