SoniTranslate and Auto-Synced-Translated-Dubs
Both tools accomplish the same core objective—translating video audio and generating dubbed tracks with synchronized speech—making them direct competitors in the video dubbing space, though they may differ in underlying TTS providers and synchronization approaches.
About SoniTranslate
R3gm/SoniTranslate
Synchronized Translation for Videos. Video dubbing
Extracts audio from videos using speaker diarization (Pyannote), translates transcribed content across 100+ languages, and synthesizes new audio with voice cloning to match original speaker characteristics. Built on Gradio for the web interface, it integrates Hugging Face models for speech recognition and generation, with GPU acceleration via CUDA for real-time processing. Deployable locally, on Google Colab, or via Hugging Face Spaces for browser-based video dubbing without manual subtitle editing.
About Auto-Synced-Translated-Dubs
ThioJoe/Auto-Synced-Translated-Dubs
Automatically translates the text of a video based on a subtitle file, and then uses AI voice services to create a new dubbed & translated audio track where the speech is synced using the subtitle's timings.
Supports multiple translation engines (Google Translate, DeepL) and TTS providers (Google Cloud, Azure, Eleven Labs) with configurable voice selection per language. Uses subtitle timings to calculate required speech duration, then either time-stretches synthesized audio or performs two-pass synthesis to match original pacing—Azure TTS can specify duration natively, eliminating stretching. Includes companion tools for batch YouTube operations: adding audio tracks to video files, translating titles/descriptions, and syncing auto-generated transcripts via the YouTube API.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work