'audio-ai' 검색 결과

AssemblyAI is a hosted speech-to-text API that transcribes audio and video files or live streams and adds speaker labels, sentiment, entity detection, PII redaction and LLM analysis of the transcript. Use when a user asks to transcribe a recording, label who said what, analyze call sentiment, redact personal data, stream live transcription, or summarize and question a transcript with LLM Gateway (the replacement for LeMUR).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.