Transcribe audio and video recordings into text with speaker diarization.
npx skills add https://github.com/garochee33/DSH --skill transcribe-garochee33
Please help me install this Agent Skill. Skill: transcribe Source: https://github.com/garochee33/DSH/tree/main/agents/skills/transcribe Command: npx skills add https://github.com/garochee33/DSH --skill transcribe-garochee33
This Skill removes the manual burden of listening to recordings and typing out what was said, making audio and video content searchable and reusable.
Ask for a transcription of the provided audio file, and specify whether you want plain text, diarized output, or speaker hints.
High-intent search queries and answers about installing and using this skill.
Transcribe audio recordings with speaker diarization by providing the file and enabling speaker separation. The Skill labels who said what in multi-speaker recordings and outputs structured speaker segments.
Yes, OpenAI transcription models are required to convert speech to text. The Skill uses these models to process audio or video recordings into searchable transcript text.
Known-speaker hints improve speaker labeling by providing reference audio samples for expected speakers. The Skill uses these hints to accurately assign names to diarized speaker segments.
Long audio files are handled through configurable chunking, which splits the recording into manageable segments for transcription. This ensures repeatable results across extended interviews or lectures.
Speech-to-text transcription supports configurable response formats, allowing you to specify plain text or diarized output. This flexibility accommodates various workflows like meeting notes or publishing.
MuhammadUATranscribe speech from audio and video files to text using Whisper APIs.
rbkayzTranscribe audio files into text using OpenAI Whisper models.
DanialHaseebTranscribe audio files into text or speaker-labeled JSON segments.
jaimedhenriquesTranscribe audio and video recordings into text with optional speaker diarization.
