Left is faster. Higher reads more hard parts right.
ElevenLabs v3 is better on non-streaming latency and naturalness. Fish Audio S2.1-Pro is better on streaming latency, 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.
ElevenLabs v3. ElevenLabs v3: 320 ms. Fish Audio S2.1-Pro: 333 ms.
ElevenLabs v3. ElevenLabs v3: 320 ms. Fish Audio S2.1-Pro: 333 ms.
Fish Audio S2.1-Pro. ElevenLabs v3: Can't stream. Fish Audio S2.1-Pro: 321 ms.
Neither has a figure. ElevenLabs v3: No stop message. Fish Audio S2.1-Pro: No stop message.
Fish Audio S2.1-Pro. ElevenLabs v3: 87.2%. Fish Audio S2.1-Pro: 92.0%.
Fish Audio S2.1-Pro. ElevenLabs v3: $40.00. Fish Audio S2.1-Pro: $15.00.