An SRT subtitle file next to your video, with the spoken words and their timings.
About
Takes a video in your workspace (MP4, MOV, WebM, M4V or MKV), extracts its audio, transcribes the speech and saves an SRT subtitle file with the same name next to the video. If the video has no spoken voice, it says so and writes nothing.
It is for captioning a talking-head clip or pulling a transcript out of uploaded footage.
Each transcription is a paid call to a speech-to-text model, billed by the length of the audio. In Syvon a typical minute of audio costs about $0.006. It currently runs only in Syvon's cloud studio, through Syvon services; a version that runs on your machine would need FFmpeg to extract the audio.
- TypeScript
- FFmpeg
- AI speech-to-text
Requirements
- Runs with
- Node.js 20 or later
- Operating systems
- windows, macos, linux
- Needs installed
- FFmpeg
- Network
- Sends the video's audio to the speech-to-text provider over the internet.
Costs
- External costs
- OpenAI: billed to your own key — Planned direct lane: you would bring your own OpenAI key. Today the call runs through Syvon services and Syvon credits.