Inworld TTS

Inworld TTS is a realtime text-to-speech API for developers building voice apps, agents, and games. It speaks 500+ languages and dialects, with expressive voices you can steer in plain words, instant voice cloning, and first audio in as little as 50 ms. Try voices in the TTS playground. The On-Demand plan starts free and includes up to 70 minutes of TTS for evaluation and prototyping, plus 100 custom voices. Beyond that, usage is billed per million characters from $7.