Left is faster. Higher reads more hard parts right.
Inworld TTS-2 is better on non-streaming latency, streaming latency, accuracy and naturalness. Soniox TTS RT v2 is better on stopping 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.
Inworld TTS-2. Inworld TTS-2: 126 ms. Soniox TTS RT v2: 241 ms.
Inworld TTS-2. Inworld TTS-2: 126 ms. Soniox TTS RT v2: 241 ms.
Inworld TTS-2. Inworld TTS-2: 127 ms. Soniox TTS RT v2: 183 ms.
Soniox TTS RT v2. Inworld TTS-2: No stop message. Soniox TTS RT v2: 0 ms.
Inworld TTS-2. Inworld TTS-2: 93.4%. Soniox TTS RT v2: 83.6%.
Soniox TTS RT v2. Inworld TTS-2: $25.00. Soniox TTS RT v2: $14.81.