On-Device-KI · WebGPU

Untertitel erzeugen und lokal übersetzen.

Verwandle jedes Video oder Audio in getaktete SRT-, VTT- oder ASS-Untertitel – mit wortgenauem Editor und einer zweiten Sprache, komplett im Browser.

GPU wird erkannt…
Zweisprachige Ausgabe
100 % privat
Warum Untertitel-Studio

Untertitel in Sende-Qualität. Ohne Upload.

Whisper-Transkription, Marian-Übersetzung und ein echter Untertitel-Editor – alles lokal.

100 % privat

Dein Material verlässt das Gerät nie. Dekodierung, Transkription und Übersetzung laufen lokal.

WebGPU-beschleunigt

Die Transkription läuft auf der GPU, wenn verfügbar, mit WebAssembly-Fallback.

Wortgenaue Zeiten

Zeitgestempelte Whisper-Modelle liefern Wort-Zeitstempel für enge Untertitel und Karaoke-Export.

Zweisprachige Ausgabe

Übersetze in eine zweite Sprache und exportiere beide Spuren in beliebiger Reihenfolge.

So funktioniert es

Vom Material zu Untertiteln.

  1. 01

    Video oder Audio ablegen

    MP4, WebM, MP3, WAV oder M4A hineinziehen – lokal dekodiert, nichts wird hochgeladen.

  2. 02

    Whisper schreibt die Untertitel

    Sprache wird in überlappenden Fenstern transkribiert und dann auf Sende-Regeln normiert.

  3. 03

    Bearbeiten, übersetzen, exportieren

    Untertitel im Studio korrigieren, Übersetzung ergänzen, dann SRT, VTT, ASS, TXT oder JSON laden.

Complete guide

About the subtitle generator

A free video-to-subtitle tool that listens to your audio with Whisper, writes timed cues, and can translate them into a second language — all inside the browser. It is built for creators, teachers, journalists and anyone captioning interviews, lectures, screen recordings or vlogs without handing raw footage to a cloud service.

How it works

The audio track is decoded with the Web Audio API and resampled to 16 kHz mono, then transcribed by a Whisper model running through Transformers.js. The file is walked in overlapping 30-second windows, so long recordings stream progress as they go and word-level timestamps stay accurate across window boundaries. Because the tool uses the timestamped Whisper builds, every cue also carries per-word timings, which drive the karaoke preview and the ASS karaoke export.

For translation, compact Marian (OPUS-MT) models are used, pivoting through English when the source and target have no direct model. Both the transcription and the translation models download once and are then cached, so a second run of the same language pair works offline.

Editing and quality

Generated cues are not set in stone. The studio pairs a live preview — with a broadcast-style subtitle overlay and a waveform timeline you can scrub — with a cue editor that supports inline text edits, splitting at the playhead, merging, duplicating, search & replace across both tracks, global time shifting, and full undo/redo. A quality panel flags every cue whose duration, reading speed, line length or overlap breaks normal subtitle conventions, and one click re-normalises the whole document.

Finished subtitles export as SRT, WebVTT, ASS, plain text or structured JSON, in the original language, the translation, or both stacked in either reading order.

Limits & requirements

The first run downloads model weights, which is the slowest step; afterwards they are cached. WebGPU (Chrome or Edge) makes transcription several times faster, and Safari or Firefox fall back to WebAssembly. Translation uses compact open models that are strong for general conversation and narration but should not be trusted for legal, medical or otherwise high-stakes wording. Very long recordings can exhaust memory on low-RAM devices; splitting the file is the workaround.

Privacy

Cloud captioning services receive your unedited footage and your scripts. Here nothing is uploaded: the video is decoded, transcribed and translated on your own machine, and the only files that leave the tab are the subtitles you choose to download.

Support

Fragen, beantwortet.

Nein. Die Datei wird im Browser dekodiert, transkribiert und übersetzt. Nur die Untertiteldatei, die du herunterlädst, verlässt den Tab.