TTS & STT Landscape in SpringโSummer 2026: On-Device Breakthroughs, API Consolidation, and Open-Source Acceleration
A comprehensive overview of text-to-speech and speech-to-text developments from April to July 2026, covering on-device breakthroughs (Supertonic, Kokoro), cloud API evolution (xAI Grok, OpenAI Realtime, Gemini 3.1 Flash), the TTS Arena leaderboard with 74 ranked models, MOSS-TTS open-source family, browser-based STT, and voice cloning comparisons.