Language tested
8 text-to-speech (TTS) models, ordered speed first: by speed tier and P95 time to first audio on Coval, then the models Coval does not measure, by name. No combined score.
Data checked on October 22, 2026 · updated after each benchmark capture
8 of the 119 text-to-speech (TTS) models in this benchmark were tested in Korean by Artificial Analysis (controlled-voice arena) or Speko (multilingual board). A model missing from this page was not tested in Korean: that does not mean it cannot speak Korean.
A model is listed here only when an independent benchmark measured its output in Korean. The list is ordered speed first, on Coval's English latency measurements: no public source measures latency in Korean. The model pages give every measurement and its date.
Amazon Polly Generative is a proprietary text-to-speech (TTS) API from Amazon, measured by one independent benchmark, Artificial Analysis.
Cartesia Sonic 3.5 is a proprietary text-to-speech (TTS) API from Cartesia, measured by three independent benchmarks: Artificial Analysis, Coval and Speko.
ElevenLabs Eleven v3 Conversational is a proprietary text-to-speech (TTS) API from ElevenLabs, measured by two independent benchmarks: Artificial Analysis and Speko.
Google Gemini 3.1 Flash TTS is a proprietary text-to-speech (TTS) API from Google, measured by two independent benchmarks: Artificial Analysis and Speko.
Inworld Realtime TTS-2 is a proprietary text-to-speech (TTS) API from Inworld, measured by three independent benchmarks: Artificial Analysis, Coval and Speko.
MiniMax Speech 2.6 HD is a proprietary text-to-speech (TTS) API from MiniMax, measured by two independent benchmarks: Artificial Analysis and Speko.
OpenAI GPT-4o mini TTS is a proprietary text-to-speech (TTS) API from OpenAI, measured by two independent benchmarks: Coval and Speko.
Rime Coda is a proprietary text-to-speech (TTS) API from Rime, measured by three independent benchmarks: Artificial Analysis, Coval and Speko.