OpenAI Whisper

Transcribe an audio/video file to text using local Whisper CLI. No API key required — runs entirely on the local machine. Supports: mp3, mp4, m4a, wav, flac, ogg, webm, mkv, avi, etc. Args: audio_url: URL of the audio/video file to transcribe. Must be publicly accessible. model: Whisper model to use. Options: tiny / base / small / medium / large / turbo (default). Smaller = faster, larger = more accurate. language: Source language code (e.g. "zh", "en", "ja"). Auto-detected if not provided. output_format: Output format. Options: txt (default) / srt / vtt / json / tsv. - txt: plain text transcript - srt/vtt: subtitles with timestamps - json: detailed segments with timestamps

Translate audio/video speech to English text using local Whisper CLI. Automatically detects the source language and translates to English. No API key required — runs entirely on the local machine. Args: audio_url: URL of the audio/video file to translate. Must be publicly accessible. model: Whisper model to use. Options: tiny / base / small / medium / large / turbo (default). Smaller = faster, larger = more accurate. output_format: Output format. Options: txt (default) / srt / vtt / json / tsv.