agents can transcribe an audio file: the transcribe_audio tool, through the harness and the speech-to-text service

hive-agent-mcp/src/mcp/args.rs

@@ -13,6 +13,15 @@ pub struct MarkTodosDoneArgs {
     pub ids: Vec<i64>,
 }
 
+/// MCP tool args for `transcribe_audio`.
+#[derive(Debug, serde::Deserialize, schemars::JsonSchema)]
+pub struct TranscribeAudioArgs {
+    /// Absolute path of the audio file to transcribe (a regular file, at most
+    /// 6 MiB; Ogg, WAV, FLAC, MP3, AMR, `MP4`/`M4A` or `WebM`). For a matrix voice
+    /// memo, the `path` that `download_file` returned.
+    pub path: String,
+}
+
 /// MCP tool args for `remind`. Exactly one of `delay_seconds` or
 /// `at_unix_timestamp` must be set; both / neither is a tool-side error.
 /// Hides the tagged `ReminderTiming` enum behind a flatter schema so the