- Home
- AI Dubbing Software
- Open Dubbing
On the recordRead 10 Oct 202622 facts
Open Dubbing
Meliana, Valencia, Spain
On the record
- Dependencies
- The README says FFmpeg is required, and espeak-ng is additionally needed when using Coqui TTS.github.com · read 9 Oct 2026
- Editing
- Users can edit generated utterance metadata, including translated text, voice gender, and speed, then rebuild the dubbed video.github.com · read 10 Oct 2026
- Hosted service
- Softcatalà offers a free test dubbing service for English or Spanish videos dubbed into Catalan, with a 2 GB or 60-minute upload limit and MP4 format support.softcatala.org · read 10 Oct 2026
- Hosted service support
- The hosted service says processing time depends on the queue and that users receive an email when dubbing is complete.softcatala.org · read 10 Oct 2026
- Installation
- The README gives a pip installation command and lists FFmpeg as an additional dependency on Linux, macOS, and Windows.github.com · read 10 Oct 2026
- Interface
- The project describes itself as an experimental command-line tool.github.com · read 9 Oct 2026
- Languages
- Available source and target languages depend on the selected speech synthesis and translation systems.github.com · read 10 Oct 2026
- License
- The repository is published under the Apache-2.0 license.github.com · read 10 Oct 2026
- Limitations
- The project describes itself as experimental and warns that errors can occur at each stage of automatic dubbing.github.com · read 10 Oct 2026
- Live service
- Softcatala’s public dubbing service is free, accepts English or Spanish videos for Catalan dubbing, and labels itself a test service that may produce errors.softcatala.org · read 9 Oct 2026
- Local execution
- The README says it is built on open-source models and can run locally.github.com · read 9 Oct 2026
- Local use
- The project is built on open source models and can run locally as a command-line tool.github.com · read 10 Oct 2026
- Purpose
- Open Dubbing is an experimental AI dubbing system that automatically translates and synchronizes dialogue into other languages.github.com · read 10 Oct 2026
- Speech processing
- Its documented workflow separates speech from background audio, identifies speakers, transcribes and translates dialogue, synthesizes speech, and assembles the dubbed video.github.com · read 9 Oct 2026
- Speech recognition
- Speech-to-text options include faster-whisper and Hugging Face Transformers implementations of Whisper.github.com · read 10 Oct 2026
- Subtitles
- The command-line tool can add original-language or dubbed subtitles as streams in the output video.github.com · read 10 Oct 2026
- Supported systems
- The README gives installation instructions for Linux and macOS and says Windows works but has not been tested extensively.github.com · read 9 Oct 2026
- Translation
- The documented translation engines are Meta NLLB and the Apertium-compatible API.github.com · read 10 Oct 2026
