Transcribes audio and video files into structured text and timestamped segments using the OpenAI Whisper API.
The AI Audio Transcription skill provides a robust server-side implementation for converting speech to text within Next.js applications. By leveraging OpenAI's Whisper model, it generates high-accuracy transcriptions complete with word-level and segment-level timestamps. This skill simplifies the complex task of handling multipart form data, validating media formats, and managing API limits, making it an essential tool for developers building podcasting apps, meeting recorders, or accessibility-focused features.
主要功能
01Word-level and segment-level timestamping for precise media mapping
02Broad support for audio/video formats including MP3, WAV, MP4, and WEBM
03Secure server-side API implementation with integrated authentication checks
04Normalized confidence scores for every transcribed segment
05Automatic file validation for MIME types and a 25MB size limit
063 GitHub stars
使用场景
01Converting recorded meetings or interviews into searchable text documents
02Building accessibility tools that provide high-fidelity speech-to-text conversion
03Creating automated subtitles and captions for video hosting platforms
