Transcribe audio files into text or speaker-labeled JSON segments.
npx skills add https://github.com/DanialHaseeb/dotfiles --skill transcribe-danialhaseeb
Please help me install this Agent Skill. Skill: transcribe Source: https://github.com/DanialHaseeb/dotfiles/tree/main/codex/skills/transcribe Command: npx skills add https://github.com/DanialHaseeb/dotfiles --skill transcribe-danialhaseeb
Turn recorded speech into clean, usable text and optionally label who spoke when, removing the manual effort of listening, summarizing, and annotating audio recordings.
Run the transcribe CLI on a recording to produce a readable transcript or a diarized JSON with speaker labels.
High-intent search queries and answers about installing and using this skill.
To transcribe audio with speaker labels, you can use the diarization feature by providing up to four known-speaker references. The Skill outputs a diarized JSON file containing speaker-labeled segments for meetings and interviews.
Yes, transcribing audio files requires an OpenAI API key and the openai Python SDK. The Skill uses OpenAI's speech-to-text models to convert recordings into accurate text or diarized JSON outputs.
Yes, you can transcribe long audio files because the Skill supports automatic chunking. It automatically splits longer audio recordings into manageable segments to ensure reliable speech-to-text processing.
The best way to convert podcast audio to text is using the CLI's fast text-first model for quick turnarounds. It processes podcasts and outputs clean plain text transcripts ready for publication or note-taking.
Speech-to-text transcription supports text, JSON, and diarized JSON output formats. You can save these outputs under a structured output directory for evaluation, archival, or downstream note-taking.
Yes, audio transcription supports batch processing for single or multiple files. It handles multiple recordings and saves the resulting transcripts or diarized JSON segments in a structured directory.
northseadlTranscribe audio files into text using OpenAI Whisper models.
mindmorassConverts meeting transcripts into structured summaries highlighting decisions, actions, and topics.
badlogicTranscribe audio files to plain text via the Groq Whisper API.
shirulotTranscribe audio and video files into text with speaker diarization using OpenAI models.
