Any recording with speech → ready-to-load SRT and VTT subtitle files, plus a plain-text transcript.
Files are encrypted
EXAMPLE
DEMO.MP4 · PRODUCT WALKTHROUGH
arrow_forward
DEMO.SRT · DEMO.VTT
00:00:01,200 --> 00:00:04,800
Welcome back. Today we are looking
at the new export flow in detail.
demo.srt · demo.vtt · demo.txt 3 files
What you get
check_circleAn SRT file that loads in every major editor and desktop player
check_circleA WebVTT file for HTML5 video and web players
check_circleA plain-text transcript of everything spoken
check_circleStandard two-line cues, at most 42 characters per line
check_circleA clear message if the file has no audio or no speech
How it works
1Upload one recordingDrop in an audio or video file up to 500 MB: a talking-head video, a screen recording, a podcast episode, a lecture.
2We transcribe and time the cuesThe speech is transcribed on our own servers in silence-aligned chunks, then shaped into standard two-line cues of up to 42 characters per line.
3Download your subtitle filesAn SRT, a WebVTT, and a plain-text transcript, all named after your upload and ready to load into your editor or player.
Who uses this tool
VIDEO PRODUCTION
Subtitles for the edit
Generate an SRT from the rough cut and drop it straight into Premiere, Resolve, or Final Cut instead of typing cues by hand.
SOCIAL MEDIA
Captions before you post
Most feeds play on mute. Add subtitles to a clip so the message lands even with the sound off.
EDUCATION
Course videos students can follow
Caption lectures and course recordings so students can watch in quiet spaces and search what was said.
PODCASTING
Captions and show notes in one run
One upload gives you subtitle files for the video version and a transcript to build show notes from.
MARKETING
Demo videos that work on mute
Subtitle product walkthroughs and webinars so prospects skimming with the sound off still get the pitch.
ACCESSIBILITY
Captions for viewers who need them
Give deaf and hard-of-hearing viewers a synced caption track instead of leaving the audio unreachable.
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 audio and video: MP3, M4A, WAV, AAC, FLAC, OGG, OPUS, WMA, and video like MP4, MOV, M4V, WEBM, MKV, and AVI. For video we extract the audio track first, then transcribe the speech. One file per job, up to 500 MB and about 60 minutes of audio — longer recordings are rejected up front with a clear message, so split them first.
Cue timing comes from silence-aligned speech chunks, which keeps subtitles in sync with the dialog for normal viewing. It is not word-level karaoke timing, so individual words are not highlighted as they are spoken.
No. Cues hold the spoken words shaped into standard two-line blocks of up to 42 characters per line, with no speaker names. For a talking-head video or narration that is exactly what you want; for a multi-person panel you would need to add names yourself.
Three files: SRT (the format editors and desktop players expect), WebVTT (the format HTML5 video and web players expect), and a plain-text transcript with the timing stripped. If you only need one format, the Video to SRT and Video to VTT tools produce a single file.
Subtitling 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 bitrate for the format (about 1 MB per minute for MP3 audio, more for WAV, FLAC, or video), so a typical minute works out to about 5 credits. The minimum is 5 credits.
Yes. Files run on our own servers, are never used to train any model, and are auto-deleted 7 days after the job finishes.