Transcribe audio with optional speaker diarization and known-speaker references.
npx skills add https://github.com/Canepro/codex-skills --skill transcribe-canepro
Please help me install this Agent Skill. Skill: transcribe Source: https://github.com/Canepro/codex-skills/tree/main/skills/transcribe Command: npx skills add https://github.com/Canepro/codex-skills --skill transcribe-canepro
Transcribing audio into accurate, readable text is often slow and error-prone, especially when speakers must be identified.
Run the bundled transcribe CLI on your audio file to generate a transcript, with optional diarization and known-speaker references.
High-intent search queries and answers about installing and using this skill.
Audio transcription with speaker diarization labels who spoke when in interviews and meetings. You provide an audio file and optional known-speaker references, and the CLI outputs labeled transcripts in plain text or structured JSON.
An OpenAI API key is required to transcribe audio files. The CLI uses OpenAI models to process multiple input audio formats, allowing you to configure chunking control and output locations for automation pipelines.
Audio transcription can output as diarized JSON or plain text. The diarized JSON format structures speaker labels and timestamps, fitting automation pipelines that require machine-readable interview and meeting transcripts.
Automating meeting transcription uses a CLI-driven approach with known-speaker references to label participants. It provides deterministic runs with model and output format controls, delivering quick, labeled transcripts for media archives.
Audio transcription supports long media archives through chunking control. This breaks extended audio files into manageable segments, ensuring accurate diarization and speaker labeling without exceeding processing limits.
Speaker diarization identifies who spoke when in interview audio transcription. It uses known-speaker references to label segments accurately, solving the problem of slow, error-prone manual identification in multi-speaker recordings.
steipeteTranscribe audio files into text using the OpenAI Whisper API.
DanialHaseebTranscribe audio files into text or speaker-labeled JSON segments.
dralkhConvert documents, media, and archives into clean Markdown.
VYRE-StudiosTranscribe speech from audio files into text using OpenAI Whisper models.
