Transcribe audio files to text with optional speaker diarization.
npx skills add https://github.com/thimslugga/agent-skills --skill transcribe-thimslugga
Please help me install this Agent Skill. Skill: transcribe Source: https://github.com/thimslugga/agent-skills/tree/main/skills/media/transcribe Command: npx skills add https://github.com/thimslugga/agent-skills --skill transcribe-thimslugga
Transcribe audio into readable text with optional diarization and speaker labeling to simplify content review, indexing, and search.
Transcribe an interview recording to text using the bundled CLI and default settings.
High-intent search queries and answers about installing and using this skill.
You can transcribe audio to text with diarization by using the bundled CLI and enabling the diarize option. This process attributes transcript segments to known speakers to simplify content indexing and review.
Yes, you can transcribe multiple audio files at once. The Skill supports processing single or multiple audio files simultaneously and saves the resulting text transcripts to your specified output paths.
Yes, you need an OpenAI API key to transcribe audio. The process requires setting the OPENAI_API_KEY environment variable to access the gpt-4o-mini-transcribe model for speech-to-text conversion.
The file size limit for speech-to-text conversion is approximately 25 MB per file. The system automatically applies chunking for longer audio recordings to process them successfully.
Yes, audio transcription runs are deterministic and reproducible. The bundled CLI ensures consistent results across multiple runs, while language hints help guide the speech-to-text model for accurate output.
Add speaker references to an audio transcript by providing known speaker information alongside the diarize option. This labels transcript segments with the correct speakers during the transcription process.
storyclaw-officialGenerate speech audio from text using the OpenAI Audio API.
DanialHaseebTranscribe audio files into text or speaker-labeled JSON segments.
TheSoftwareHouseClean raw workshop transcripts into structured documents with topics, decisions, and action items.
MoRen9527Transcribes audio files locally with OpenAI Whisper CLI to text or SRT subtitles without API keys.
