A city clerk wants searchable text from evening council-meeting audio. The recordings are English speech, not photos, and the clerk is not asking to change the language. Which AWS service matches this job?

Evening council-meeting audio that must become searchable English text is a speech-to-text job, which Amazon Transcribe provides. Transcribe matches because the input is spoken English audio and the desired output is text in the same language for search, not a translation and not a spoken rendering of written minutes. Amazon Translate changes text from one language into another; it does not consume meeting audio as the primary input for this clerk requirement and would not create the first transcript. A computer-vision service that labels objects in still images operates on pixels and never hears the council recording, so it cannot produce searchable speech logs. Amazon Polly turns written text into spoken audio—the opposite direction of what the clerk needs when starting from recordings. The stem already notes the recordings are English speech, not photos, and that the clerk is not asking to change the language, which eliminates vision and Translate. Exam caveat: match AWS speech and language services by transform direction (audio→text, text→text language change, text→audio) rather than by the vague idea of "working with language." Operational check: feed a short council clip to Transcribe, confirm the transcript is searchable English, and verify Translate or Polly are not required unless a later language or read-aloud step is explicitly added.