Left is faster. Higher reads more hard parts right.
Gradium TTS is better on non-streaming latency, streaming latency and naturalness. Soniox TTS RT v2 is better on stopping, 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.
Gradium TTS. Gradium TTS: 76 ms. Soniox TTS RT v2: 241 ms.
Gradium TTS. Gradium TTS: 76 ms. Soniox TTS RT v2: 241 ms.
Gradium TTS. Gradium TTS: −64 ms. Soniox TTS RT v2: 183 ms.
Soniox TTS RT v2. Gradium TTS: No stop message. Soniox TTS RT v2: 0 ms.
Soniox TTS RT v2. Gradium TTS: 79.5%. Soniox TTS RT v2: 83.6%.
Soniox TTS RT v2. Gradium TTS: $36.00. Soniox TTS RT v2: $14.81.