Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This study introduces a comprehensive corpus of transcribed religious radio broadcasts from over 2,000 AM and FM stations in the U.S., recorded during July 2025. Utilizing an automated pipeline for transcription and speaker diarization, the dataset comprises more than 700,000 recordings and 60 million lines of speech, categorized by programming format and topic with the aid of a large language model. This resource enables in-depth analysis of religious broadcasting's role in social and political discourse, addressing a significant gap in mass communication research.
Over 60 million lines of speech from religious radio broadcasts reveal how faith-based media engages with social and political issues across the U.S.
Religious radio is a widespread but understudied form of mass communication in the United States, and content-level analysis of it has been constrained by the absence of large-scale transcript data. This Data Descriptor presents a corpus of transcribed English-language religious radio broadcasts captured from live webstreams over a one-month period in July 2025. Fifteen-minute segments were recorded on a rolling schedule from 785 distinct streams, which together rebroadcast the signals of more than two thousand AM and FM stations, yielding over 700,000 recordings and more than 60 million diarized lines of speech. Each recording was transcribed and speaker-diarized with an automated pipeline, and segmented and labeled by programming format and topic using a large language model. The corpus is organized as linked tables of stream metadata, recording metadata, and transcript lines. It supports descriptive study of religious broadcasting across regions and traditions, analysis of how social and political issues are discussed in religious media, and speech-processing research in an underrepresented domain.