Does it add timestamps or speaker labels?

No. You get the spoken words as recognized, verbatim and in order, grouped into readable paragraphs. There are no timestamps and no speaker names, so it is best for capturing what was said rather than who said it or exactly when. If you need timed captions, use our subtitle generator instead.

Do I get a video back?

No. The output is text: a plain-text transcript and a formatted DOCX, both named after your recording. Your original video is untouched.

How is pricing calculated?

Transcription is 5 credits per minute of audio. Because the length is not known until the file is processed, the upfront hold is estimated from file size at a typical video bitrate (about 8 MB per minute), so a typical minute works out to about 5 credits. The minimum is 5 credits.

Are my recordings private?

Yes. Recordings run on our own servers, are never used to train any model, and are auto-deleted 7 days after the job finishes.

4242tools

← All tools

Video to Text

Video → text · DOCX5 credits per minute

Zoom, Teams, lecture, and webinar recordings → a typed transcript of everything said, as TXT and DOCX.

Files are encrypted

EXAMPLE

WEEKLY-SYNC.MP4 — ZOOM RECORDING

arrow_forward

WEEKLY-SYNC.TXT

Thanks everyone for joining, let us dive in.

The rollout finished ahead of schedule.

We still need a decision on the pricing page.

weekly-sync.txt · full transcript text

What you get

check_circleA plain-text transcript of everything spoken

check_circleA formatted DOCX with your recording name as the title

check_circleThe audio track extracted from the video automatically

check_circleSpeech transcribed as spoken, not summarized or reworded

check_circleA clear message if the video has no audio or no speech

How it works

1Upload one videoDrop in a recording up to 500 MB — a Zoom or Teams call, a recorded lecture, a webinar, or any other video with speech.

2We extract and transcribe the audioThe audio track is pulled out of the video, converted to the shape the speech model needs, and transcribed on our own servers.

3Download the transcriptA plain-text file and a formatted DOCX, both named after your recording, with the words grouped into readable paragraphs.

Who uses this tool

TEAMS & MEETINGS

Zoom and Teams calls, written up

Turn a recorded call into text you can search, quote, and paste into your notes — no replay needed.

EDUCATION

Recorded lectures as study text

Transcribe a lecture recording so students can read, highlight, and revise instead of scrubbing video.

MARKETING

Webinars turned into content

Transcribe a webinar to repurpose it as blog posts, follow-up emails, and a searchable archive.

HR & RECRUITING

Recorded interviews on the page

Transcribe a recorded video interview so the answers are in text you can review and compare.

CUSTOMER SUPPORT

Training videos, made searchable

Transcribe internal training recordings so the team can search for the answer instead of rewatching.

RESEARCH

Recorded sessions, transcribed

User research and study sessions on video become text you can read, code, and analyze.

SECURITY

Built for sensitive documents

Bank statements, medical files, case records. Security isn't a feature we added — it's the foundation.

lock

Encrypted in transit

Encrypted in transit over TLS 1.2+, and stored in access-controlled, encrypted object storage. Files are protected the moment they leave your browser.

admin_panel_settings

Your files stay yours

Workspaces are isolated per account. Role-based access shows teammates only what they need.

auto_delete

Deleted, not stored

Files are deleted after processing. Everything runs on our own hardware and is never sent to an outside AI service, so your data is never used to train models.

dnsProcessed on our own hardwareauto_deleteDeleted after processinglockEncrypted in transit

Questions

Common video formats: MP4, MOV, M4V, WEBM, MKV, and AVI. One recording per job, up to 500 MB and about 4 hours of audio — longer recordings are rejected up front with a clear message. We extract the audio track first, then transcribe the speech — the video itself is not analyzed.