Left is faster. Higher reads more hard parts right.
Rime Coda is better on non-streaming latency, streaming latency and naturalness. MAI-Voice-2.1-Flash is better on accuracy and price.
Last updated Methodology by Dileep Chagam
Measure by measure, the same sentences, the same place.
An estimate: speech-to-text transcribers scored it, not people.
The same sentence, read by each voice.
Rime Coda. Rime Coda: 282 ms. MAI-Voice-2.1-Flash: 289 ms.
Rime Coda. Rime Coda: 282 ms. MAI-Voice-2.1-Flash: 289 ms.
Rime Coda. Rime Coda: 269 ms. MAI-Voice-2.1-Flash: Can't stream.
Neither has a figure. Rime Coda: No stop message. MAI-Voice-2.1-Flash: No stop message.
MAI-Voice-2.1-Flash. Rime Coda: 76.7%. MAI-Voice-2.1-Flash: 78.3%.
MAI-Voice-2.1-Flash. Rime Coda: $50.00. MAI-Voice-2.1-Flash: $15.00.