The best of 25 voices at keeping costs low
Price per 1M characters: $14.81
Soniox TTS RT v2: the best of 25 voices at keeping costs low. Its weakest is medical terms, tied 19th of 26.
Last updated Methodology by Dileep Chagam
Where it ranks among all 26 voices, in plain words.
Nothing in the bottom quarter of the voices.
The first read of each test sentence, unedited.
Pick any voice to set against it. Every pair has its own page.
Soniox TTS RT v2 starts in 241 ms on a typical sentence (median) and 290 ms on the slowest 1 in 10 (p90), 7th of 26 voices.
Soniox TTS RT v2 starts in 241 ms on a typical sentence (median) and 290 ms on the slowest 1 in 10 (p90), 7th of 26 voices.
Yes. With streamed text, Soniox TTS RT v2 starts 183 ms after the last word arrives.
Yes. After the stop it still sends 0 ms of audio (median), which the agent throws away.
Soniox TTS RT v2 read 83.6% of the hard parts right, as speech-to-text heard it. Its weakest kind is numbers and shorthand, at 77.8%. This is an estimate, not a listening test.
Soniox TTS RT v2 lists at $14.81 per million characters.