AI live captions are now built into Android, Windows, and iOS, and dedicated apps like Live Transcribe and InnoCaption add even more capability. Most options are free or low-cost and work without any special equipment — just your phone or computer.
AI has made real-time speech-to-text genuinely useful in daily life — not perfect, but close enough to change how people who are deaf or hard of hearing navigate conversations, phone calls, meetings, and media. The best news is that many of the best tools are already on devices you own.
Here is a practical breakdown of what's available, what each tool does best, and how to turn it on.
Built-in OS Captions (No Download Required)
Before reaching for a separate app, check what your device already offers. These built-in features have improved significantly in recent years.
Android: Live Transcribe
Google's Live Transcribe turns your Android phone into a real-time captioning device. Point the microphone toward whoever is speaking and read captions on screen. It shows pauses, identifies different speakers, and can even detect environmental sounds like laughter or applause.
How to enable: Settings → Accessibility → Live Transcribe. On Pixel phones it may be in the quick settings panel.
Cost: Free.
Best for: Face-to-face conversations, group settings, anywhere you can hold your phone.
Windows: Live Captions
Windows 11 includes Live Captions, which transcribes any audio playing through or into your computer — including video calls, streaming video, microphone input, and system audio. It runs as a floating bar you can dock to the top or bottom of your screen.
How to enable: Settings → Accessibility → Captions → Live Captions, or press Windows key + Ctrl + L.
Cost: Free with Windows 11.
Best for: Video calls, streaming video, online meetings, any computer audio.
Apple: Live Captions (iPhone/iPad and Mac)
Apple's Live Captions transcribes speech in real time and integrates with FaceTime. On supported devices, it can caption FaceTime calls automatically.
How to enable: Settings → Accessibility → Live Captions (toggle on).
Cost: Free on supported devices.
Best for: FaceTime calls, iPhone conversations, Mac audio.
Dedicated Apps for More Capability
| App | Platform | Best for | Cost | Notes |
|---|---|---|---|---|
| Live Transcribe | Android | In-person conversations | Free | Offline mode available |
| InnoCaption | iOS / Android | Phone calls | Free (FCC-certified) | Real captioners assist AI |
| Otter.ai | iOS / Android / Web | Meetings, recordings | Free tier; paid plans | Saves searchable transcripts |
| Ava | iOS / Android | Group conversations | Free tier; paid plans | Multi-speaker tracking |
| Google Meet captions | Web / App | Video meetings | Free with Google account | Auto-enabled in Meet settings |
| Zoom auto-captions | Web / App | Video meetings | Free tier | Enabled in accessibility settings |
InnoCaption (Recommended for Phone Calls)
InnoCaption is designed specifically for captioning phone calls. It uses a combination of AI and human captioners to transcribe the other person's speech in real time while you talk normally. It is certified by the FCC under the Telecommunications Relay Service program, meaning it is provided at no cost to people with hearing loss.
How it works: You make calls through the InnoCaption app. Captions appear on screen as the other person speaks.
Setup: Download the app, create a free account, and verify eligibility.
Otter.ai (Recommended for Meetings and Recordings)
Otter.ai transcribes meetings, interviews, lectures, and recordings. It identifies different speakers, saves searchable transcripts, and integrates with Zoom, Google Meet, and Microsoft Teams. It is not designed for real-time face-to-face conversation but excels for recorded or structured sessions.
Captions for TV and Streaming
Most streaming services now include captions as standard. A few things worth knowing:
- Netflix and Amazon Prime both offer closed captions. Look for the CC or speech-bubble icon during playback.
- YouTube auto-generates captions for most videos. They're imperfect but often usable. You can also search for videos that include human-made captions.
- Smart TVs have accessibility menus that can enable captions across all apps.
For anything playing on a Windows computer, the built-in Live Captions feature can overlay captions on any video, regardless of whether the video's source offers them.
Tips for Getting the Best Results
A few practices make AI captions work significantly better:
Reduce background noise. AI captioning accuracy drops with competing sounds. When possible, find a quieter spot or ask the other person to speak more slowly.
Position the microphone correctly. For phone apps, the microphone faces the speaker — not toward you. For computer apps, a directional microphone rather than a built-in laptop mic makes a real difference.
Use wired headphones for calls. Bluetooth audio sometimes introduces a slight delay that can throw off caption timing.
Enable speaker identification. Apps like Otter.ai and Ava label each speaker separately, which makes multi-person conversations much easier to follow.
What to try next
If you are interested in broader accessibility tools, AI Tools for Low Vision: What's Worth Using covers screen readers, magnification, and image description features. For a general introduction to AI assistants on your phone, ChatGPT Voice Mode explains how voice-based AI works and what to expect from it.
