openai-whisper

To transcribe audio files into text with timestamps, you can use this Skill to convert meeting recordings, voice memos, or interviews into readable, time-stamped written transcripts automatically.

Yes, you need an OpenAI API key and network access to api.openai.com to convert speech to text, as the transcription and translation processes rely on OpenAI's Whisper infrastructure.

Yes, you can translate non-English audio into English text. The Skill processes spoken audio from common formats and outputs the translated English written content directly.

The best way to handle batch transcription for multiple audio files is using the Skill's batch processing feature, which transcribes higher volumes of meeting recordings or voice memos in one workflow.

Yes, audio transcription works for common audio formats. It is specifically designed to process meeting recordings, voice memos, and interviews, turning them into accurate written text.

Limitations for speech-to-text conversion include requiring active network access to api.openai.com and a valid OpenAI API key, as the Skill cannot perform offline transcription or batch processing without them.