This study analyzes the use of social media sources by nine news outlets in Chile in regard to Covid-19. We identified the most frequently used types of sources, their evolution over time, and the differences between the various social media platforms used by the Chilean media during the pandemic. Specifically, we extracted 838,618 messages published by Chilean media on Facebook, Instagram, and Twitter between January and December 2020. An initial machine learning (MA) process was applied to automatically identify 168,250 messages that included keywords that link their content to Covid-19. Based on a list of 2,130 entities, another MA process was used to apply a set of rules based on the appearance of declarative verbs or common expressions used by the media when citing a source, and the use of colons or quotation marks to detect the presence of different types of sources in the news content. The results reveal that Chilean media outlets’ use of different voices on social media broadly favored political sources followed by health, citi-zen, academic-scientific, and economic ones. Although the hierarchy of the most important sources used to narrate the public health crisis tended to remain stable, there were nuances over time, and its variation depended on key historic milestones. An analysis of the use of sources by each platform revealed that Twitter was the least pluralist, giving space to a more restricted group of voices and intensifying the presence of political sources over the others, particularly citizen sources. Finally, our study revealed significant differences across media types in the use of political, health, and citizen sources, with television showing a greater presence than in other types of media.