Text in die Rede KI-Agenten Musik Audio zu Text Stimme Klonen Sprachgestaltung Marktplatz Mehr
Report Bug / Feature Request

AI Video Dubbing

Upload a video, pick a target language and voice, and download a fully dubbed copy. End-to-end pipeline runs automatically.

Kostenlos anmelden

1. Upload Your Video

Please log in to dub videos. Free accounts get 1 minute per upload.

Drag a video here or click to browse

MP4, MKV, MOV, WebM, AVI, M4V — up to 200 MB Free: up to 1 minute per video

2. Dubbing Options

3. Progress

Upload a video to begin.

0%
  1. Extracting audio
  2. Transcribing speech
  3. Translating segments
  4. Generating speech
  5. Time-aligning audio
  6. Muxing into video

4. Dubbed Video

Download

Video Dubbing Plans

Starten Sie kostenlos, aktualisieren Sie, wenn Sie mehr benötigen

Free Account
  • Up to 1 minute per video
  • Up to 200 MB upload
  • 30+ target languages
  • Auto source language detection
  • One-click end-to-end pipeline
Am beliebtesten
Pro
  • Up to 30 minutes per video
  • Priority GPU queue
  • API access
  • All standard + premium voices
  • Auto-refund on failure
Kostenlos anmelden

Häufig gestellte Fragen

Video Dubbing is the one-click pipeline: upload a video, pick one target language and one voice, and we run extract → transcribe → translate → synthesize → time-align → mux automatically. The Dubbing Studio is the editor flow where you can review the transcript, change voices per speaker, and tweak timing before generation.

MP4, MKV, MOV, WebM, AVI, and M4V containers. Files are capped at 200 MB. Free accounts can dub up to 1 minute per upload; paying accounts can dub up to 30 minutes per upload.

Roughly 1-2x video length on average — a 5-minute video typically finishes in 5-10 minutes. The progress bar shows the current pipeline stage (extracting, transcribing, translating, synthesizing, aligning, muxing) so you know where you are.

Each translated segment is time-stretched (atempo) to fit its original time slot, capped at 1.3x to keep the voice intelligible. If a segment still overruns its slot, the next segment shifts later instead of getting cut off. The final audio is concatenated with silence padding to match the original video length.

Not in this one-click flow — for line-by-line review use the Dubbing Studio at /dubbing/. Video Dubbing is optimized for speed and a single, predictable output.

A flat 5,000 characters per minute of video, billed up-front and refunded automatically if the pipeline fails. A 10-minute video costs 50,000 characters; a 30-minute video costs 150,000 characters.

Both the source upload and the dubbed output live in your account's media folder. The cleanup_jobs cron deletes them along with the job row after 2 days; you should download the dubbed video before then if you want to keep it.

In v1 you pick from the standard catalog of voices. Persistent voice clones (UserVoice) and per-segment voice selection are on the roadmap.

Any of the 30+ target languages our TTS catalog supports. Source language can be auto-detected by Whisper or set explicitly. We use translateapi.ai's batch endpoint to translate all segments in a single round-trip.

Not in v1 — we replace the entire audio track with the dubbed speech. For background-preserving dubbing, use the Dubbing Studio at /dubbing/ which runs source separation.
5.0/5 (1)

Was könnten wir verbessern? Ihr Feedback hilft uns, Probleme zu beheben.

Bereit für den Anfang?

Melde dich kostenlos an und erhalte 15.000 Zeichen. Keine Kreditkarte erforderlich.

Kostenlos anmelden Preise anzeigen