This ComfyUI workflow leverages the ElevenLabs API to convert speech from audio or video files into accurate, editable text. By integrating several key nodes, including LoadAudio, RecordAudio, ElevenLabsSpeechToText, and PreviewAny, this workflow provides a seamless process for speech transcription. The LoadAudio and RecordAudio nodes allow users to either upload pre-existing audio files or capture new audio directly within the interface. Once the audio is loaded, the ElevenLabsSpeechToText node processes the audio data, converting it into text with high accuracy. Finally, the PreviewAny node lets users review the transcribed text, ensuring it meets their needs before exporting or editing further. This workflow is particularly useful for content creators, journalists, and researchers who need reliable and efficient transcription services.