Left is faster. Higher reads more hard parts right.
Deepgram Flux is better on non-streaming latency and streaming latency. Soniox TTS RT v2 is better on stopping, accuracy, naturalness 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.
Deepgram Flux. Deepgram Flux: 194 ms. Soniox TTS RT v2: 241 ms.
Deepgram Flux. Deepgram Flux: 194 ms. Soniox TTS RT v2: 241 ms.
Deepgram Flux. Deepgram Flux: 154 ms. Soniox TTS RT v2: 183 ms.
Soniox TTS RT v2. Deepgram Flux: 80 ms. Soniox TTS RT v2: 0 ms.
Soniox TTS RT v2. Deepgram Flux: 77.4%. Soniox TTS RT v2: 83.6%.
Soniox TTS RT v2. Deepgram Flux: $45.00. Soniox TTS RT v2: $14.81.