audio-transcriber

You can transcribe audio to text locally by running the Skill with your audio file path and specifying a Whisper model. It processes the recording entirely on your machine using OpenAI Whisper for accurate voice-to-text conversion.

Yes, you can generate subtitles from an MP3 file. This Skill transcribes the audio and outputs results in multiple formats including SRT and VTT, which are standard subtitle file types for video integration.

You can convert various audio formats including MP3, WAV, and OGG files. The Skill accepts these common audio file types and transcribes them using the Whisper model into your chosen text, subtitle, or JSON format.

Yes, local transcription supports automatic language detection and translation. The Whisper model identifies the spoken language in the audio and can translate the recording into English text during the transcription process.

Yes, you can adjust the quality and speed trade-off when transcribing audio. The Skill allows you to select different Whisper models, such as the medium model, to balance transcription accuracy against local processing time.