Left is faster. Higher reads more hard parts right.
Cartesia Sonic 3.5 is better on naturalness and price. Deepgram Flux is better on non-streaming latency, streaming latency, stopping and accuracy.
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.
Deepgram Flux. Cartesia Sonic 3.5: 261 ms. Deepgram Flux: 194 ms.
Deepgram Flux. Cartesia Sonic 3.5: 261 ms. Deepgram Flux: 194 ms.
Deepgram Flux. Cartesia Sonic 3.5: 244 ms. Deepgram Flux: 154 ms.
Deepgram Flux. Cartesia Sonic 3.5: 809 ms. Deepgram Flux: 80 ms.
Deepgram Flux. Cartesia Sonic 3.5: 73.1%. Deepgram Flux: 77.4%.
Cartesia Sonic 3.5. Cartesia Sonic 3.5: $39.20. Deepgram Flux: $45.00.