Tied for best of 26 voices at reading read from context right
Read from context: 100%
Fish Audio S2.1-Pro: tied for best of 26 voices at reading read from context right. Its weakest is streaming latency, 15th of 18.
Last updated Methodology by Dileep Chagam
Where it ranks among all 26 voices, in plain words.
The first read of each test sentence, unedited.
Pick any voice to set against it. Every pair has its own page.
Fish Audio S2.1-Pro starts in 333 ms on a typical sentence (median) and 403 ms on the slowest 1 in 10 (p90), 16th of 26 voices.
Fish Audio S2.1-Pro starts in 333 ms on a typical sentence (median) and 403 ms on the slowest 1 in 10 (p90), 16th of 26 voices.
Yes. With streamed text, Fish Audio S2.1-Pro starts 321 ms after the last word arrives.
Fish Audio S2.1-Pro has no stop message, so the agent has to close the connection to stop it.
Fish Audio S2.1-Pro read 92.0% of the hard parts right, as speech-to-text heard it. Its weakest kind is codes and addresses, at 85.7%. This is an estimate, not a listening test.
Fish Audio S2.1-Pro lists at $15.00 per million characters.