speech-transcriber

To transcribe audio and video into timestamped text, this Skill processes media files using Whisper or alternative ASR backends. It automatically detects language and outputs text with word-level timing.

Yes, you can generate SRT subtitles from video and audio recordings. The Skill outputs SRT format alongside TXT and JSON, providing word-level timing for accurate captions and accessible media content.

Whisper supports automatic language detection for podcast transcription and other media inputs. The Skill detects the spoken language without manual configuration and handles multiple audio and video formats.

The best way to get word-level timestamps for lecture transcripts is using an ASR backend like Whisper. This Skill processes lecture audio and video to produce JSON outputs with precise word-level timing for indexing.

Supported output formats when transcribing media content include TXT, SRT, and JSON. The JSON and SRT formats contain timestamps, enabling searchable transcripts and downstream processing for captions.

You need a local environment configured for Whisper or alternative ASR backends to run transcription. The Skill has no external dependencies, supporting local processing of audio and video into timestamped text outputs.