One video or recording → subtitle files already translated into the language your viewers read, as SRT and VTT.
Files are encrypted
EXAMPLE
DEMO.MP4 — ENGLISH SPEECH
arrow_forward
DEMO-SPANISH.SRT
00:00:01,200 --> 00:00:04,700
Bienvenidos a la demo de hoy.
Empecemos con el panel de informes.
demo-spanish.srt · demo-spanish.vtt 2 files
What you get
check_circleSRT and VTT files already in your target language
check_circleCues capped at two lines and broadcast line lengths
check_circleTiming kept from the original speech — only the words change
check_circleNames, numbers, and untranslatable terms left as spoken
check_circleSubtitle files only — we never burn them into the video
How it works
1Upload one video or recordingDrop in a video or audio file up to 500 MB and type the language you want the subtitles in.
2We transcribe, then translateThe speech is transcribed on our own servers, shaped into readable two-line cues, and every cue is translated into your target language with its timing kept.
3Download SRT and VTTTwo subtitle files named after your upload and language, ready to load into your player, editor, or platform.
Who uses this tool
VIDEO & YOUTUBE
Captions for a second audience
Upload the finished cut once and publish caption tracks your international viewers can actually read.
ONLINE COURSES
Lessons your students can follow
Turn a recorded lesson into translated subtitles so learners can study in the language they know best.
MARKETING
One demo, many markets
Localize a product demo or launch video with subtitle files ready for every platform you post on.
LOCALIZATION
A first pass worth editing
Hand your reviewers timed, translated cues to polish instead of raw audio to transcribe from scratch.
EVENTS & WEBINARS
Replays that travel
Give a recorded talk or webinar a subtitle track in the language of the region you are expanding into.
PODCASTING
Video episodes, subtitled abroad
Publish the video version of an episode with translated captions instead of leaving listeners to guess.
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 and audio recordings: MP4, MOV, M4V, WEBM, MKV, AVI, and audio like MP3, M4A, WAV, AAC, FLAC, OGG, OPUS, and WMA. For video we extract the audio track first. 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.
Type any target language — Spanish, Brazilian Portuguese, Japanese, whatever your audience reads. Quality is strongest for widely spoken languages; for rarer ones, treat the output as a first draft to review.
Timing is derived from silence-aligned speech chunks, not word-level alignment, so cues land close to the speech but not frame-perfect. There are also no speaker labels. For most published videos this is well within watchable range; for broadcast-grade sync, plan a manual pass.
No — we never output a video file. You get SRT and VTT sidecar files, which load into YouTube, video editors, and media players, and keep your original video untouched.
Transcription plus translation is 8 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). The minimum is 8 credits.
Yes. Recordings run on our own servers, are never used to train any model, and are auto-deleted 7 days after the job finishes.