Left is faster. Higher reads more hard parts right.
Grok TTS is better on streaming latency, stopping, accuracy and price. Smallest Lightning v3.1 is better on non-streaming latency and naturalness.
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.
Smallest Lightning v3.1. Grok TTS: 358 ms. Smallest Lightning v3.1: 357 ms.
Smallest Lightning v3.1. Grok TTS: 358 ms. Smallest Lightning v3.1: 357 ms.
Grok TTS. Grok TTS: 157 ms. Smallest Lightning v3.1: 363 ms.
Grok TTS. Grok TTS: 0 ms. Smallest Lightning v3.1: No stop message.
Grok TTS. Grok TTS: 87.4%. Smallest Lightning v3.1: 81.3%.
Grok TTS. Grok TTS: $15.00. Smallest Lightning v3.1: $19.50.