Transcripts you can check.
Upload audio or video and get back a transcript with punctuation and a timestamp on every word — in 21 languages. Any line plays back the second it came from. Fix what the machine got wrong.
Free to start. No card.
Weekly sync
Demo · no audio0:04 / 0:38 · 2 speakersSpeaker 1
Speaker 2
Speaker 1
A transcript arrives like this: numbered speakers, not names. Rename one — the name carries through every turn. Clicking a line moves the playhead here; in the app it plays the recording from that second.
An illustration of the output format, not a recording.
- languages
- 21languagesThe picker lists 24 variants
- variants with speaker labels
- 12 of 24variants with speaker labelsThe rest arrive as one speaker
- timestamps
- Word-leveltimestampsClick a line to hear it
- export formats
- 4export formatsTXT · SRT · VTT · DOCX
- longest file on Pro
- 8 hlongest file on ProOne upload, one transcript
01/How it works
Upload it, read it, check it.
Drop in a file or record in the browser. You get back a transcript with a timestamp on every word — then check any line against the audio, and put the transcript to work.
Drop audio or video
interview.m4astandup.mp4orRecordStep 01Upload or record
Audio or video, dropped in or picked from a folder. Or record straight from the browser — nothing to install.
- 0:04
Speaker 1
0:11Speaker 2
0:13Speaker 1
Step 02Read the transcript
Speakers separated, punctuation in, a timestamp on every word. 21 languages; speaker labels on 12 of the 24 variants in the picker.
- SummaryTranslationChatExportAnswers cite the second they came fromStep 03
Check it, then use it
Click any line to hear it and fix what was misheard. Then summarise, translate, ask it questions or export.
02/The transcript
Fix it yourself, fast.
No recogniser gets names, jargon or crosstalk right every time. Click a paragraph and correct it — your edit doesn't break the timings. Rename a speaker once and the name follows the whole transcript.
Every word timed
Checking a quote takes a second, not a scrub.
Click any line to hear it. The transcript follows as it plays, so checking a quote takes a second rather than a scrub.
- The word being spoken is marked as it plays
- Click a word to play from exactly there
- Timecodes sit in their own column, so they never jitter
Speaker 2
We never voted on the second tranche. It was added to the budget after the committee had already signed off.
Speaker 1
Who added it?
Speaker 2
I'd rather not say that on the record.
Yours to correct
Fix a misheard name once.
Click a paragraph and fix it. The timings survive your edit, and a custom word list stops the same mistake twice.
- Offers to make the same fix everywhere else — and says how many places first
- Split a paragraph, merge two, or move a line to the right speaker
- Every edit can be undone, and it saves as you go
Speaker 1
Thanks for making time. You were on the committee when the second tranche came up?
Speaker 2
I was. Shivon Siobhan Murphy chaired it, and she was clear it had to go back to the full council
Shivon → Siobhan appears in 6 other places across 4 paragraphs.
Fix allNot nowVocabulary
One per line, or separated by commas.
03/Ask it questions
Every claim keeps its source.
Summaries are drawn only from what was said. Answers come back with the moment they came from. So when it matters, you check it in two seconds instead of taking it on faith.
Speaker 2
We never voted on the second tranche. It was added to the budget after the committee had already signed off.1
Speaker 1
Who added it?
Speaker 2
I'd rather not say that on the record.2
Speaker 1
Could the chair have added it on her own?
Speaker 2
Not without the finance office knowing about it.
Did she say who added the second tranche?
No. She says it was added after the committee had signed off, and declines to say who added it.
- 112:04“It was added to the budget after the committee had already signed off.”
- 212:14“I'd rather not say that on the record.”
Copy with sourcesRegenerate
- Cites the moment
- Each answer lists the lines it used, with their timecodes. Click one and the recording plays from there.
- Only from the transcript
- Answers come only from what was said, not from what a model happens to know about the subject.
- Says what it didn't read
- If a recording is too long to read in one go, the answer says how much of the middle it didn't see — instead of letting you assume it read everything.
04/Summaries
It knows what you recorded.
A sales call and a user interview need different notes. Pick what you recorded and the summary is shaped for it.
Get the quote right.
Themes, quotes worth keeping, and claims worth checking.
What the summary is made of
- 01Themes
- 02Notable quotes
- 03Claims to check
Budget committee: the second tranche
A committee member describes how a second tranche entered the budget after committee sign-off, and declines to say who added it.
Themes
- How the second tranche entered the budget
- Who had the authority to add it
Notable quotes
- “We never voted on the second tranche.”
- “I'd rather not say that on the record.”
Claims to check
- The tranche was added after the committee had signed off
- The finance office would have known about it
An illustration of the summary format, not a real recording.
Most tools flatten an argument into a tidy paragraph. Ours keeps the open questions open, quotes people in their own words, and records a request as a request — not as a recommendation.
05/Put it to work
Translate it, export it, share it.
A free account is the whole product with 90 minutes in it, not a demonstration of it. Summaries, translation, questions, share links and every export format are on every plan.
Translation in place
Read it in another language line by line, original underneath, timings intact.
The first version of the book was six hundred pages long.
La primera versión del libro tenía seiscientas páginas.
And how many were left?
¿Y cuántas quedaron?
Two hundred. And I still think fifty of those are too many.
Doscientas. Y todavía creo que sobran cincuenta.
Export
Plain text, subtitles or a Word document — straight from the transcript.
Share a read-only page
Anyone with the link can read it, without getting access to your account.
Anyone with this link can read it
Include the audio or video
Include the summary
Record in the browser
Interviews, meetings, voice notes — straight from the microphone, nothing to install. The dot says whether audio is actually arriving, not just whether recording started.
- Waiting for audio
- Audio arriving
- Stopped arriving
06/Limits
Where it falls over.
Every transcription tool has these. Most don't mention them.
Recording
Transcript
No gap, no warning — it looks complete.
One file, one language
Auto-detect settles on one language for the whole recording. What was said in the other may come back translated instead of transcribed, or not come back at all — and nothing is marked as missing, so the transcript will look complete. Name the main language if you know it.
- zh-CN
- zh-TW
- yue
- en-US
- en-GB
- en-IN
- ja
- ko
- es
- fr
- de
- it
- pt
- ru
- hi
- vi
- th
- id
- ms
- tr
- ar
- nl
- pl
- uk
Speaker labels One speaker
Speaker labels on 12 of 24 variants
The other 12 variants transcribe with full timings and punctuation, but everything arrives as one speaker. You see this before you upload, not after.
Long recordings drift
Past about twenty minutes, speaker labels can wander — a consequence of how long audio is processed, not a setting. We wrote up why.
07/Free tools and writing
Useful before you sign up.
Notes on building a transcription tool, including where ours falls over — and two tools that need no account.
19 September 2026 · 9 min read
When "auto-detect language" quietly translates instead of transcribing
In bilingual recordings, automatic language detection can hand you fluent English for something that was said in Chinese — and because the output reads perfectly, nobody catches it.
19 September 2026 · 6 min read
Why a three-hour interview comes back with eleven speakers
Speaker labels drift on long recordings, and the reason isn't that the model is bad at voices. It's that long audio gets cut into pieces, and each piece counts from one.
19 September 2026 · 7 min read
What "99% accurate" actually means
Every transcription company advertises the same number. Here's where it comes from, why your recording won't reproduce it, and the question worth asking instead.
08/Questions
Before you upload.
Anything not here, write to support@txscribe.ai.
Can I try it without an account?
Yes. Put one recording of up to 10 minutes through it — upload it or record it — and you get a real transcript back, with no account and no card. It is kept for 48 hours; sign in if you want to keep it.
What if the transcript is wrong?
Then you fix it — that's the part we built most carefully. No recogniser is perfect on names, jargon or people talking over each other. The editor keeps your timings, and a custom word list stops the same mistake recurring.
Which languages, and which get speaker labels?
21 languages. The picker lists 24, because some of them come in more than one regional variant. Speaker separation is available on 12 of those 24: Chinese (Mandarin), English (US), English (UK), English (India), Japanese, Korean, Spanish, French, German, Italian, Portuguese (Brazil) and Hindi. The other 12 transcribe with full timings and punctuation, but everything arrives as one speaker. The picker tells you before you upload, not after.
What if a recording switches between languages?
Name the main language rather than leaving it on automatic. Detecting the language automatically means settling on one for the whole recording, and what was said in the other may come back translated instead of transcribed — or not come back at all. Either way nothing is marked as missing: the transcript will look complete.
What happens to my recordings?
They're stored so you can play them back beside the transcript, and deleted with the transcript when you delete it. They are never used to train anything.
How much does it cost?
A free account starts with 90 minutes, once — enough to put one real recording through and judge it. Pro is for people who transcribe every week. See pricing.
Judge it on your own recording.
Ours is the only transcript we can vouch for, and it isn't yours. Run something real through it — that's the only test that means anything.
Free to start. No card.