Fact · Dictation in your apps
Claude's current API models accept text and image input and produce text output, and the models overview lists no audio input.
Checked against its source on October 17, 2026
In the source's own words
“All current models support text and image input, text output, multilingual capabilities, vision, and tool use.”
Models overview (Claude API documentation), Anthropic, Anthropic (Claude API documentation), 2026, Models overview.
Open the original- What it measures
- The page lists the input types for each current model.
- What it does not show
- It is a list of supported inputs, not proof that audio can never be sent. Check the current docs before building on it.