Transcribe audio to text using OpenAI models with optional speaker diarization.
npx skills add https://github.com/cloudofgeorge/AI-hands --skill transcribe-cloudofgeorge
Please help me install this Agent Skill. Skill: transcribe Source: https://github.com/cloudofgeorge/AI-hands/tree/main/skills/transcribe Command: npx skills add https://github.com/cloudofgeorge/AI-hands --skill transcribe-cloudofgeorge
Transcribes audio to text using OpenAI models, with optional speaker diarization to label segments.
Run the bundled transcribe CLI on an audio file to generate a transcript.
High-intent search queries and answers about installing and using this skill.
To transcribe audio with speaker diarization, you can use this tool to label speaker segments in meetings and interviews. It leverages OpenAI models to process single files or batches, outputting diarized JSON to label individual speakers.
The best way to batch transcribe podcasts is by using this tool to convert audio into text, JSON, or diarized JSON formats. It processes multiple podcast files with optional language hints, saving searchable transcripts directly to your output directory.
Yes, you can use OpenAI models to transcribe audio with known-speaker references. This feature allows you to provide speaker identifiers during the transcription process, improving diarization accuracy for interviews and multi-speaker recordings.
Audio transcription supports chunking controls and optional language hints to optimize processing. These features allow you to manage large audio files and specify the spoken language, ensuring accurate transcriptions saved as text or JSON.
Yes, you need the OpenAI dependency to convert speech to text using this tool. It relies on OpenAI models for core transcription and diarization logic, requiring valid API access to process audio files and generate output transcripts.
Available output formats for transcribing field recordings include plain text, JSON, and diarized JSON. These formats support downstream processing, with transcripts automatically saved by default to the output/transcribe directory for easy retrieval.
bl1nk-botTranscribe audio files into text transcripts with optional speaker diarization.
akselikorhonen-siiliExtract HTML content from web pages and convert it to Markdown.
GongLingRuiSplit long text into uniform chunks at sentence or paragraph boundaries.
tara-shoposGenerate short product videos from images or descriptive text.
