Left is faster. Higher reads more hard parts right.
Inworld TTS-2 is better on accuracy, naturalness and price. Gradium TTS is better on non-streaming latency and streaming latency.
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. Inworld TTS-2: 126 ms. Gradium TTS: 76 ms.
Gradium TTS. Inworld TTS-2: 126 ms. Gradium TTS: 76 ms.
Gradium TTS. Inworld TTS-2: 127 ms. Gradium TTS: −64 ms.
Neither has a figure. Inworld TTS-2: No stop message. Gradium TTS: No stop message.
Inworld TTS-2. Inworld TTS-2: 93.4%. Gradium TTS: 79.5%.
Inworld TTS-2. Inworld TTS-2: $25.00. Gradium TTS: $36.00.