Extract a movie's full audio and generate timestamp-aligned SRT subtitles.
npx skills add https://github.com/AubreyHan/SKILL_Repo --skill get-movie-subtitles
Please help me install this Agent Skill. Skill: get-movie-subtitles Source: https://github.com/AubreyHan/SKILL_Repo/tree/main/get-movie-subtitles Command: npx skills add https://github.com/AubreyHan/SKILL_Repo --skill get-movie-subtitles
This Skill turns a full movie or video soundtrack into a clean, aligned subtitle file, removing the manual effort of transcribing dialogue and timing captions.
Ask for subtitles for your movie file and specify the target language so the Skill can extract the full audio, generate translated SRT captions, and return the finished subtitle file.
High-intent search queries and answers about installing and using this skill.
To generate an SRT subtitle file from a full movie, the Skill extracts the entire audio track using ffmpeg to preserve native timestamps, then transcribes and translates the speech into an SRT file using the Gemini API.
Yes, you can translate video subtitles while keeping the original timing by processing the full audio track with Gemini, which translates the transcribed speech and outputs a timestamp-aligned SRT file.
Yes, transcribing long-form video requires ffmpeg and ffprobe for audio extraction, the google-genai Python SDK, and a configured GEMINI_API_KEY to run the speech-to-text and translation processes.
The best way to transcribe a full film's audio track is to use a tool that extracts the complete soundtrack with ffmpeg and processes it via the Gemini API, producing a clean SRT file without manual chunking.
Yes, temporary and uploaded audio files are cleaned up automatically after the Gemini API processes the full audio track and generates the final SRT subtitle file, ensuring storage efficiency.
google-geminiGenerate and edit videos with the Gemini Omni Flash model via the google-genai SDK.
jianshuoSegment long-form videos into themed clips using SRT timestamps and ffmpeg.
dislerExtracts audio, converts video to MP4 or WebM, and transcribes with Whisper via Python CLI.
steipeteTranscribe audio files into text using the OpenAI Whisper API.
