GuidesBy featurePeople who are deaf or hard of hearing, and anyone in a noisy room or a place they need to keep quiet

Caption any video, call or voice note with one tap

For People who are deaf or hard of hearing, and anyone in a noisy room or a place they need to keep quiet.

Start here

What this helps you do: Android Live Caption puts live captions on almost any audio your phone plays, from videos to phone calls to voice notes, with a single tap. It runs on the device, so it works offline and the audio is never sent to Google. Confirm anything consequential another way.
What you leave with: A repeatable workflow and a starter prompt you can adapt to your own work.
What to check before trusting it: You confirm anything consequential, like a name, a dose, a date or legal wording, another way, because captions can misfire

When to use this

You want to follow a video, a phone call or a voice note without relying on the sound, whether that is because you are deaf or hard of hearing, or because the room is loud or has to stay quiet.

Captions speech on your phone with a single tap, no setup for each new video or call
Works across videos, podcasts, phone calls, video calls and audio messages
Runs on the device, so it captions offline and your audio is never stored or sent to Google

Workflow

Turn Live Caption on in settings, or add it to the volume shortcut so it is one tap away
Play the video, call or voice note and read the captions as they appear
For a name, a dose, a date or legal wording, confirm it another way, by asking the speaker or checking a written source
Remember it works on the device, so you do not need an internet connection for it to caption
Turn it off when you are done if you would rather not caption everything

Prompts to try

Use it, adapt it, and make it your own.

Live Caption on my phone wrote this term in a medical or legal context, but I am not sure it heard it right. List the likely correct spellings or meanings and how I should confirm which one is right.

Ask Bit to adapt it →

Human lens

You confirm anything consequential, like a name, a dose, a date or legal wording, another way, because captions can misfire
You decide when a caption is good enough to act on and when you need to hear or read the real thing
You treat the captions as a live aid, not a record you can rely on later

What to avoid

Captions can get names, medical and legal terms and numbers wrong, so confirm anything consequential another way
Accuracy drops with strong accents, background noise and fast overlapping speech
The captions are a live aid, not a transcript you can lean on as an official record

Related guides

View all →

Giving a persistent agent one job without handing over the keys

Agents that run on their own cloud computer stay signed in to your tools between sessions. That persistence is the point, and it means the thing you are really configuring is access, not prompts.

Using deep research without trusting it blindly

Deep research modes read many sources and return a longer, cited answer. They are powerful for a first pass, and they still need you to check the sources and the reasoning.

Letting an assistant take multiple steps on its own

Agentic modes plan a task, take a sequence of actions such as browsing, running code or editing files, and check their own progress along the way. They can save real time on chores with several steps, and they can also wander off course, so you set the boundaries and check the outcome.

Using projects to keep AI in context, not starting over

Projects or workspaces let you gather files, instructions and past chats in one place, so the assistant carries the right context into every new conversation instead of you repeating it each time.

Reviewed 19 September 2026