speech-transcriber

To transcribe audio with timestamps, this Skill processes video files using Whisper for speech recognition, generating SRT subtitles and JSON outputs with word-level timing for precise content analysis. You simply provide the local video file path to initiate the transcription process.

You can generate SRT subtitles for video editing by running this Skill on downloaded videos. It utilizes Whisper for speech recognition to automatically convert audio tracks into timestamped SRT files, making it easier to search content and prepare editing clips.

Yes, you need ffmpeg, Whisper, and yt-dlp installed as dependencies. This Skill utilizes Whisper for the core speech recognition and relies on ffmpeg to handle audio extraction from video files before generating timestamped text outputs.

The best way to automate JSON transcription for video content analysis is using this Skill, which converts audio to text with timestamps. It generates JSON outputs containing word-level timing data, enabling precise content searching and detailed video analysis.

Yes, this Whisper transcription approach works with local mp4 files. You can transcribe the audio from any local mp4 file by providing the file path, allowing the Skill to extract audio and generate timestamped SRT and JSON outputs.