Your recordings, transcribed with speaker labels.
What it does
Turns audio and video recordings into transcripts with speaker labels and timestamps, and prepares recordings for transcription.
When to use it
Use for transcription, speaker separation, subtitles, audio conversion, downsampling, merging recording segments, or preparing smaller uploads for Feishu Minutes.
How to use it
Give it recordings or media URLs; it returns saved transcripts with speaker labels and timestamps by default, or prepares the audio for transcription.
What you provide
- Your files
Uses
What you need · 10
Uses uv to run the media resolver and transcription pipeline scripts.
Uses ffprobe to validate resolved media and inspect recording duration.
Access · 6
This skill
Feishu Minutes
Uploads recordings to Feishu Minutes
ASR Endpoint URL
Sends audio to your server