Captions & transcripts

Let every word
find its audience.

Put readable live text on the right screen, capture speech in its original language, or save a transcript for later.

Three ways to work with text

Let the words do the work.

Translated subtitles

Turn speech into text in another language without generating a spoken translation. Share supported text-only audience channels or an overlay where enabled.

Same-language captions

Show speech as text in its original language, with no translated voice. Display it in the room or share a text-only caption channel.

Transcribe only

Capture an original-language transcript in a dedicated session, where enabled. Translation channels stay saved but do not run; this mode does not create audio recordings, audience streams or summaries.

Designed to be read

One conversation.
The right view for every screen.

Illustrative caption view · EnglishSentences flow

Good conversations bring us closer.

Everyone deserves a place in the room.

Let’s make the next idea a shared one.

A reading example, not a live transcription.

Choose Words or Sentences

Words flow shows incoming text as it develops; provisional words can change. Sentences flow waits for a complete sentence or a bounded fallback. Only confirmed text goes into saved files and shared caption outputs.

Give every screen a clear role

Show up to three caption panes inside the console, or open independent language windows. Use full-screen, a simplified CC view or picture-in-picture where supported. Native captions are available where enabled.

Read at your own pace

Adjust text size, colours and the reading area, show available original text and scroll back to review. Following pauses while you read earlier lines; return to the latest text when you are ready.

From a name to a technical term

Give recognition some context.

Prepare names before the event

Paste or import names and preferred spellings, then save a draft. Supported One-to-Many captions can match romanised and similar-looking forms; optional AI-assisted checks help review uncertain names where enabled.

Keep caption text focused

The filler filter can clean supported One-to-Many text and downstream saved captions. Name and filler tools act on text; they do not correct the spoken translation or guarantee accuracy.

Vocabulary Augmentation

Add preferred spellings for names, brands and technical terms under Team → Vocabulary. Up to 100 terms can guide same-language captions and Transcribe only, where recognition hints are enabled.

Keep translation terminology separate

The team translation glossary and recognition vocabulary serve different purposes. Vocabulary changes apply on the next Start and can improve recognition without guaranteeing a spelling.

Useful after the live moment

Keep the words you need.

Save SRT and Markdown

Enable subtitle files, readable transcripts or both. Saves use confirmed text, preserve available language and track information, and encrypt content before upload. Long captures may create multiple numbered files.

Connect live captions to other tools

Where enabled, send text to an OBS overlay or an external WebVTT feed. These are explicit sharing paths with their own access controls; standalone Transcribe only does not publish them.

Let everyone be part of it

Your next conversation.
A little more connected.

Open Salam.AI console

Already part of a team? Sign in to start a session.

Explore plans for your organisation →