What problem does it solve?
It converts spoken audio in video into readable subtitle text, helping teams create accessible, multi-language captions without manual transcription and timing work.
Core Features & Use Cases
- Video speech transcription: Converts an input video into subtitle formats (e.g., SRT/ASS/TXT/JSON) using selectable ASR backends such as bijian, whisper variants, or other supported options.
- Subtitle optimization and translation: Optimizes subtitle structure and timing, then translates captions into a target language using supported translators (e.g., Bing/Google/LLM).
- Subtitle burn-in synthesis: Produces a final video by burning subtitles as soft or hard subtitles, with optional consistency review to prevent subtitle/script drift.
- Use Case: A content team needs captions for an English lecture video, then wants burned hard subtitles for multiple languages while ensuring the subtitles match an approved script.
Quick Start
Use the command cli-anything-videocaptioner process video.mp4 --asr bijian --translator bing --target-language en --subtitle-mode hard to transcribe, translate, and burn hard subtitles into the video.