Transcribe audio and video files into text with speaker diarization using OpenAI models.
npx skills add https://github.com/shirulot/codex-skill --skill transcribe-shirulot
Please help me install this Agent Skill. Skill: transcribe Source: https://github.com/shirulot/codex-skill/tree/main/transcribe Command: npx skills add https://github.com/shirulot/codex-skill --skill transcribe-shirulot
This Skill removes the friction of manual transcription by leveraging OpenAI's models to convert audio and video recordings into text, including speaker identification.
Use the transcribe skill to convert the audio file meeting.m4a into a text transcript with speaker labels.
High-intent search queries and answers about installing and using this skill.
To transcribe audio with speaker diarization, this Skill uses OpenAI models to process recordings and automatically label different speakers. It converts interviews and multi-person meetings into structured, searchable text.
Yes, you can convert meeting recordings into structured text or JSON formats. The transcription processes audio and video files using OpenAI models to output clean, organized text for your records.
Yes, you need a valid OpenAI API key and the OpenAI Python SDK installed to perform speech-to-text operations. These dependencies are required to access the high-quality transcription models.
The best way to transcribe interviews and identify who said what is using a speech-to-text process with speaker diarization. This automatically labels individual speakers, generating a clean transcript of the conversation.
Yes, this transcription approach works with both audio and video files. It leverages OpenAI models to accurately turn speech from your recordings into text, regardless of the original media format.
cinienceGenerate speech audio from text using Alibaba Cloud DashScope Qwen TTS models.
SpaceZephyrSearch historical Lark video conference records and retrieve linked meeting artifacts.
euroconicAutomate audio capture, transcription, and post-processing for dictation and meeting recordings.
adbertramTranscribe local audio and video files into timestamped JSON transcripts using whisper.cpp.
