The best of 27 voices at reading codes and addresses right
Codes and addresses: 92%
AssemblyAI TTS 1: the best of 27 voices at reading codes and addresses right. Its weakest is read from context, tied 22nd of 27.
Last updated Methodology by Dileep Chagam
Where it ranks among all 27 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.
AssemblyAI TTS 1 starts in 171 ms on a typical sentence (median) and 296 ms on the slowest 1 in 10 (p90), 4th of 27 voices.
AssemblyAI TTS 1 starts in 171 ms on a typical sentence (median) and 296 ms on the slowest 1 in 10 (p90), 4th of 27 voices.
Yes. With streamed text, AssemblyAI TTS 1 starts 159 ms after the last word arrives.
Yes. After the stop it still sends 40 ms of audio (median), which the agent throws away.
AssemblyAI TTS 1 read 81.5% of the hard parts right, as speech-to-text heard it. Its weakest kind is read from context, at 70.8%. This is an estimate, not a listening test.
AssemblyAI TTS 1 lists at $15.00 per million characters.
Cekura runs these simulated calls on your agent and scores every one.