Transcribe audio files to text with optional speaker diarization.
npx skills add https://github.com/syl2042/codex_skills --skill transcribe-syl2042
Please help me install this Agent Skill. Skill: transcribe Source: https://github.com/syl2042/codex_skills/tree/main/transcribe Command: npx skills add https://github.com/syl2042/codex_skills --skill transcribe-syl2042
Transcribe audio to text with optional speaker diarization to extract readable transcripts from meetings, interviews, podcasts, and recordings. It simplifies turning audio content into searchable text and labeled speaker segments for easier review and analysis.
Run the bundled transcribe CLI on an audio file to generate a transcript, with optional diarization if you need speaker labels.
High-intent search queries and answers about installing and using this skill.
To transcribe audio with speaker labels, use the optional diarization feature to identify who spoke when. This generates readable text outputs with labeled speaker segments, making recordings easier to review and analyze.
Speaker diarization identifies who spoke when in audio recordings. By separating audio into labeled speaker segments, it converts meetings and interviews into searchable text with distinct speaker labels for easier analysis.
Yes, you need an OpenAI API key to transcribe audio files. The workflow enforces the presence of the OPENAI_API_KEY environment variable and uses the default gpt-4o-mini-transcribe model to process recordings into text.
Yes, you can transcribe multiple audio files at once. The workflow supports multiple input files and processes them using an auto chunking strategy, writing the resulting text outputs to the output/transcribe directory by default.
The best way to transcribe podcasts into searchable text is using a CLI-based workflow with optional diarization. It provides deterministic results and writes readable transcripts to a default output folder, simplifying audio content extraction.
When transcribing audio with OpenAI, expect limitations tied to the default gpt-4o-mini-transcribe model and the auto chunking strategy. Diarization is optional, and known speaker references are required for deterministic labeled speaker segments.
zhangziliang04Transcribes audio files into text using OpenAI's Whisper API via curl.
okbest2024Fetch YouTube video transcripts for summarization and content extraction.
jaimedhenriquesTranscribe audio and video recordings into text with optional speaker diarization.
lidge-junTranscribe audio files into text with speaker diarization using OpenAI's Whisper models.
