Bluez Dubbing
globluez.com
- Free plan
- Web
- API
- Self-hosted
What Bluez Dubbing is
Bluez Dubbing is an open-source pipeline for automatic video dubbing and subtitle generation, offered through a web interface, API or self-hosted setup. It can create dubbed video with burned-in subtitles, translated audio only or subtitles only. The maker says it supports more than 50 languages with automatic language detection. WhisperX supplies speech recognition, word-level timestamps and speaker diarization, while M2M-100 or deep-translator handle translation. Chatterbox voice cloning and Edge TTS generate speech in the target language. Voice-activity timing and time stretching align replacement speech, with speaker matching available. Subtitle styles include Netflix, bold desktop and mobile optimized. The web UI accepts uploads and links from YouTube, Instagram and TikTok, and provides progress tracking, previews and downloads. REST endpoints and command-line tools support automation. Models can be swapped independently. The project uses Apache 2.0; self-hosting keeps data on the operator’s servers. Quickstart requires FFmpeg and uv, and some tokenizers require a JVM.
Who it suits
Bluez Dubbing suits content creators and businesses localizing training materials. It is also suited to teams wanting self-hosted processing, APIs or interchangeable speech and translation models.
Good to know, and what to watch
- Supports more than 50 languages
- Offers dubbing, audio-only and subtitle-only modes
- Includes voice cloning
- Provides web UI, API and CLI
- Allows self-hosted data control
- Quickstart requires FFmpeg and uv
- Some tokenizers require a JVM
- Self-hosting requires operator-managed servers
The verdict
Bluez Dubbing covers automated translation, speech generation, synchronization and subtitle production in one open-source pipeline. Its setup requirements and model components should be reviewed before deployment.
What the maker publishes
- API and CLI
- The repository describes REST API endpoints and command line tools for automating the pipeline and its services. source
- Cost
- The homepage describes the self-hosted product as completely free. source
- Dubbing modes
- It supports video dubbing with subtitles, audio-only translation, and subtitling-only mode. source
- Input sources
- The repository says the web UI accepts file uploads or video links from YouTube, Instagram, and TikTok. source
- Integrations
- The maker lists WhisperX, PyTorch, FastAPI, FFmpeg, M2M-100, Edge TTS, Chatterbox, Silero VAD, pyannote, pyrubberband, and yt-dlp among its components. source
- Intended users
- The maker's guide names content creators and businesses localizing training materials as potential users. source
- Languages
- The maker says it supports more than 50 languages with automatic language detection. source
- License
- The project is released under the Apache 2.0 license. source
- Limit
- The repository quickstart requires FFmpeg and uv, and notes that some tokenizers require a JVM. source
- Modularity
- Users can swap speech recognition, translation, and text-to-speech models independently or plug in their own. source
- Purpose
- Bluez Dubbing is an open-source pipeline for automatic video dubbing and subtitle generation. source
- Security and data control
- The maker says self hosting keeps data on the operator's servers and makes the code auditable; no specific security certification is stated on the page. source
- Speech recognition
- WhisperX extracts speech with word-level timestamps and speaker diarization. source
- Subtitles
- Subtitle styles include Netflix, bold desktop, and mobile optimized, with subtitles burned into the video. source
- Support
- The maker lists [email protected] for contact. source
- Synchronization
- The pipeline uses voice activity detection based duration alignment and pyrubberband time stretching to synchronize replacement speech. source
- Translation
- The homepage names M2M-100 and deep-translator as translation options. source
- Translation and voices
- The listed options include M2M-100 or deep-translator for translation and Chatterbox voice cloning or Edge TTS for speech synthesis. source
- Voice synthesis
- The homepage names Chatterbox voice cloning and Edge TTS for generating speech in the target language. source
- Web interface
- The repository describes a web UI with live progress tracking, result previews, and downloads. source
- Workflow
- It can produce dubbed video with burned-in subtitles, audio translation, or subtitles only. source
Checked against the maker's pages on 8 Oct 2026.