Live Caption AI

Share real-time, streamed captions to millions of devices & harness the power of AI-driven technology to instantly transcribe speech among multiple speakers.

How It Works

Open the app and create an account to begin face-to-face captioning immediately. See exactly what everyone is saying in real time. Turn on "Multiple Speakers" to distinguish between different voices and change situational models for better accuracy at the doctor's office, talking to a financial advisor, or in other languages.

Use Cases

Event Producers: Make your events more accessible and shareable with real-time captions that reach all attendees.

Content Creators: Expand your audience with live transcriptions and multilingual support.

People with Hearing Loss: Stay connected and never miss a word during conversations and events.

Instantaneous Transcription: Simply speak to get accurate, real-time captions with punctuation and proper line breaks.

Remote Accessibility: Join in from anywhere with “LiveShare” Web Links, our new feature that lets you view live captions via a browser. Broadcast a sermon, a class, or a meeting to your audience.

Organized Knowledge: Save transcripts, tag them for easy retrieval, and effortlessly search through your spoken information.

Pricing

Free trial - 5-minutes

$3.99 - Unlimited Monthly Personal Captioning (on device, not streaming)

$1.49 - 15 minutes of “LiveShare” Links, stream live captions over the web

$2.99 - 30 minutes of “LiveShare” Links, stream live captions over the web

$9.99 - 120 minutes of “LiveShare” Links, stream live captions over the web

FAQs

What are the “LiveShare” weblinks for?

If you are someone who speaks to an audience, like a teacher, a keynote speaker, or a pastor in a church, you can purchase a public URL for your captions to be broadcast over live in real-time as you speak. The time does not expire “2 hours” after purchase or start. You may start and stop as much as you like on the same link, until the amount of minutes is used up.

Now your audience can follow along with every word, from the convenience of their own phone or home computer.

How do I separate multiple different speakers’ voices?

When captioning multiple people speaking at once, tap the top left Menu icon to open the list of options. Select “Caption Settings”. The first item, “Diarization,” detects multiple speakers. Select “Enable” to turn on this feature.

The app will separate the different voices heard. The AI may take about a minute to detect and separate the distinct voices.

The app can distinguish many different speakers, as high as around 12; however, the accuracy of the labeling may get worse with larger numbers.

Upon saving the transcript, you can rename the different speakers the AI distinguished.

How do get the best results?

Live Caption AI has different language models for specific situations that may be helpful. Go to Settings, and "Change Specialization Model" for different setting syou may be in. Switch for Medical for use in a doctor visit, for example. Switch to "Everyday" model to get access to more languages than the "Premium" model has available. 

How do I save the captions I have?

While on the main Captionng screen, tap “Start New”. This will give you the option to “Save Transcript” or “Discard” the captions you’ve got.

You can “Rename” the title of the Transcript, which defaults to the date and time it started transcribing.

You may also add relevant, searchable Tags to the document, which are helpful when captioning many different situations.

Final Summary

Caption face-to-face conversations in real time and broadcast event captions over the web! Stream real-time transcripts to your audience, make your message more shareable and enhance accessibility.