This is an example article. Narration generation will be connected in the next milestone; this page does not claim a voice-model benchmark.
Generate once, listen whenever
Article audio should be prepared on the main server. The small public server only needs to send the finished recording to a reader.
Write for listening
Long code blocks and tables need a prose explanation rather than a word-for-word reading of punctuation. A good narrated article preserves the argument and gives listeners enough context to follow it.
Keep recordings in sync
Each recording belongs to an exact revision of the article. If the text changes, an outdated recording should disappear until the matching audio is ready.