Live transcription

Live transcription that keeps up with the interview room

Hit record and watch the words appear on screen with sub-second latency. Translate in parallel, share a live link with a producer in another time zone, and keep a local backup running in the browser as insurance. Try the live caption demo below.

Try it now

A working sandbox. No sign-up, no project. Sample data only.

  • Sub-second latency. Most words appear on screen within a second of being spoken.
  • The browser records locally in parallel so connection drops don't lose audio.
  • Live-share link for up to 25 viewers, each picking their own translation language.
  • 20+ source languages across four providers; pick the right one per session.
  • Producer chat lets remote editors and stakeholders message the on-set producer without the interviewee ever seeing it.
LIVE · READY
demo
INTERIM CAPTIONS · ENGLISH

Click start to see interim captions stream in.

How it works

Three steps from raw material to result.

STEP 01
RECORDING
00:08:14
INTERVIEWER

When did you first realise the bridge wouldn't hold?

ELENA M.

We knew by the second week. The numbers [typing…]

Press record

Microphone audio streams from the browser to a transcription engine in real time. Interim captions appear within a few hundred milliseconds.

STEP 02
ENGLISH

We knew by the second week.

The numbers stopped making sense.

ESPAÑOL

Lo supimos a la segunda semana.

Los números dejaron de tener sentido.

25 viewers · live link active
Translate and share live

A parallel translation column updates as words land. A shareable link lets up to 25 viewers join, each picking their own target language.

STEP 03
Connection restored
Local backup found · 2m 14s gap
Re-transcribing gap from local copy…
No audio lost. Transcript complete.
Outage-proof backup

The browser keeps recording a local copy the whole time. If the network drops, any gap is filled automatically by re-transcribing the local audio when you reconnect.

Speaker recognition across every voice

Each speaker turn is fingerprinted and matched automatically. Rename once and every appearance updates, including files you uploaded weeks ago.

SPEAKERS · PROJECT-WIDE
demo
EM
Elena Marín
14 files · 6.2 h
matched
MT
Marcus Thorne
9 files · 4.7 h
matched
DR
David Reyes
7 files · 3.1 h
matched
?
Unknown Voice
2 files · 0.4 h
unmatched

Voice prints matched automatically. Rename once and the change applies to every file.

Select, highlight, send. Without leaving the transcript.

Highlight any span, add a colour marker, send the quote plus its timecode and speaker label directly to a paper cut, or copy it for use elsewhere.

TRANSCRIPT · SELECTION MODE
demo
INTERVIEWER00:24:08When did you realize the bridge wouldn't hold?
ELENA M.00:24:11We knew by the second week. The numbers stopped making sense.
INTERVIEWER00:24:19Did you tell anyone at the time?
ELENA M.00:24:22I filed a memo. Nobody read it.
MARCUS T.00:31:04I was never shown that memo.

Remote oversight without disrupting the room

Editors at HQ, executive producers, legal stakeholders, and news editorial teams can follow the session and message the on-set producer in real time. The interviewee never sees the chat.

LIVE SESSION · PRODUCER VIEW
demo
PRODUCER CHAT
Not visible to the interviewee

Waiting for messages…

LIVE TRANSCRIPT
INTERVIEWER

Walk me through the sequence of events.

SUBJECT

It was complicated. We'd been watching the situation for months.

INTERVIEWER

From the beginning: when did you first see the report?

SUBJECT

The first time I actually read it

Frequently asked questions

What's the latency like?

Most words appear within 300–800ms of being spoken, depending on the engine. The fastest engines deliver results in under half a second.

Can I switch providers mid-session?

No, but you can pick the best provider for your language before you start. The session locks to that engine for stability; the next session can pick a different one.

Does it work if my connection drops?

The browser keeps a local copy the whole time. When you come back online, any gap is filled by re-transcribing the locally saved audio against the server transcript.

How many people can watch the live share?

Up to 25 viewers per live session, each picking their own translation language independently.

What languages does live transcription support?

20+ source languages across the four providers. The dropdown shows which languages each provider supports before you start.

Who can send messages in the producer chat, and who sees them?

Anyone with the live-share link can send chat messages: a remote editor at HQ, an executive producer, a legal observer, a news director. The messages go only to the session host (the on-set producer). The interviewee or subject never sees the chat, so sensitive direction, editorial pushback, or legal guidance stays private to the production team.

Related capabilities

Further reading

Background guides and comparisons.

Put live transcription to work on your project.

Start free with 5 minutes of AI transcription a month. Or book a personalised walkthrough with the team.