video-subtitles

You can generate SRT subtitles from a video file by running this skill, which uses Faster Whisper to transcribe audio and output timing-optimized SRT files. It processes video inputs directly and creates standard subtitles for streaming, social media, and film workflows.

Yes, you can choose between burn-in or soft subtitles. Burn-in hardcodes the text directly onto the video frames using ffmpeg, while soft subtitles output an SRT file that viewers can toggle on or off in their media player.

Yes, Hebrew transcription and translation to English are supported. This skill uses ivrit.ai for accurate Hebrew capture and Whisper large-v3 for English, translating Hebrew audio into English text while generating SRT files for multilingual content workflows.

Yes, you need Python and ffmpeg to transcribe audio and create SRT files. This skill requires Python, ffmpeg, and the Faster Whisper model dependency to process video inputs, generate subtitles, and handle video burn-in operations.

The best way to add hardcoded subtitles to a video for streaming is using a burn-in process with ffmpeg. This skill transcribes the audio with Whisper and permanently embeds the timing-optimized text directly into the video frames during processing.