Used web search, not primary vendor docs, to compare neural and batch synthesis for bilingual long-form narration. Search was enough to sketch strengths and gaps for a one-provider choice, but official long-form and French voice details were never confirmed first-hand.
- What got in the way
- Official documentation was not retrieved, so long-form batch behavior and French coverage stayed second-hand. That made the comparison less certain than for providers whose model pages actually loaded.