Transcribe audio files into text using the OpenAI Whisper API.
npx skills add https://github.com/FatBy/DD-OS --skill openai-whisper-api-fatby
Please help me install this Agent Skill. Skill: openai-whisper-api Source: https://github.com/FatBy/DD-OS/tree/main/skills/openai-whisper-api Command: npx skills add https://github.com/FatBy/DD-OS --skill openai-whisper-api-fatby
This Skill automates the transcription of audio files into text, making spoken content searchable and usable.
Use the openai-whisper-api skill to transcribe the audio file '/path/to/audio.m4a' and save the output to '/path/to/transcript.txt'.
High-intent search queries and answers about installing and using this skill.
To transcribe audio to text, this Skill sends your audio files to the OpenAI Audio Transcriptions API using the Whisper model. It automates the request via cURL, allowing you to convert spoken content into searchable text transcripts.
You can convert various audio formats to text, including M4A and OGG files. The Whisper API accepts these inputs and processes them through customizable parameters like model selection, language, and output format.
Yes, you need an active OpenAI API key to execute speech-to-text transcription. The Skill also requires the cURL command-line tool to be installed in your environment to send the API requests and receive the text output.
Yes, you can customize Whisper transcription parameters by specifying the model, output file path, target language, and providing context prompts. These options help improve accuracy for specific accents or terminology in your audio files.
You automate meeting transcription by providing the path to your M4A recording and a destination for the transcript file. The Skill processes the audio through the Whisper model and outputs the converted text for easy searching and summarization.
The best way to extract text from voice notes is using the Whisper API to convert spoken content into written transcripts. This Skill outputs the text to a specified file path, making it immediately available for search, summarization, or data processing.
me2DocTranscribe audio files into text using the OpenAI Whisper API.
skinnyandbaldExtract action items from Fireflies.ai transcripts and create GitHub issues.
omeragaakbasSummarize customer interview transcripts into structured Markdown with JTBD and action items.
adbertramTranscribe local audio and video files into timestamped JSON transcripts using whisper.cpp.
