whisper-transcribe-docker

Local speech-to-text transcription processes your audio files directly on your machine using a Docker container, eliminating the need for external cloud APIs and ensuring complete data privacy. The Skill uses the faster-whisper library to convert inputs into text.

Generating speech-to-text transcripts with timestamps involves using the faster-whisper library to process audio files. This Skill optionally includes timestamps for each transcribed segment, producing detailed outputs ideal for searching and summarizing podcast episodes.

Yes, you can use Docker to run faster-whisper for audio processing on your machine. The Skill provides a Dockerfile and scripts to execute local speech-to-text transcription, supporting various model sizes and language detection for accurate results.

Yes, local transcription with faster-whisper supports various model sizes and language detection. This allows you to balance transcription accuracy and processing performance based on your local hardware capabilities while handling audio file inputs.

To output transcribed text to a specific file from a Docker container, you specify the target file path in your execution command. This Skill can output the transcription results as plain text or JSON directly to a designated file on your machine.