Inworld TTS 2.0

The smallest roster in the voice catalog, four voices, across sixteen languages, with a speed control and no emotion selector. It is built for realtime synthesis, and the characteristic that follows from that is responsiveness rather than range.

Four voices is a genuine constraint and the first thing to check against the job. For a single narrator or a two-hander it is enough; for a piece that needs a cast of distinct speakers it is not, and Gemini 3.1 Flash TTS's thirty or Kokoro's thirty-three are the places to go.

Where it earns its premium tier is consistency: a small tuned roster tends to hold character across a long script better than a large one, which matters when narration runs over many separate renders that have to sound like the same person. If the piece is one long voice across a dozen clips, that consistency is worth more than choice.