Aller au contenu

Language tested

Japanese text-to-speech: TTS APIs tested

29 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

29 of the 119 text-to-speech (TTS) models in this benchmark were tested in Japanese by Artificial Analysis (controlled-voice arena) or Speko (multilingual board). A model missing from this page was not tested in Japanese: that does not mean it cannot speak Japanese.

What "tested in {value}" means

A model is listed here only when an independent benchmark measured its output in Japanese. The list is ordered speed first, on Coval's English latency measurements: no public source measures latency in Japanese. The model pages give every measurement and its date.

Frequently asked questions

What is the best Japanese text-to-speech API in 2026?
This benchmark does not crown one: it compares speed first, then voice quality, accuracy and price, without adding them up. Of the 29 models tested in Japanese, 10 have a measured latency on Coval; the fastest on slow turns is Cartesia Sonic 3.5, with a P95 time to first audio of 381 ms (median 281 ms), measured in English.
Does a TTS API missing from this page support Japanese?
Possibly. This page lists only the models that Artificial Analysis or Speko actually tested in Japanese. A missing model was not tested in Japanese; check the provider's documentation for its supported languages.