Left is faster. Higher reads more hard parts right.
ElevenLabs v4 is better on non-streaming latency, streaming latency, naturalness and price. Gemini 3.1 Flash is better on accuracy.
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 v4. ElevenLabs v4: 678 ms. Gemini 3.1 Flash: 1.16 s.
ElevenLabs v4. ElevenLabs v4: 678 ms. Gemini 3.1 Flash: 1.16 s.
ElevenLabs v4. ElevenLabs v4: 561 ms. Gemini 3.1 Flash: Can't stream.
Neither has a figure. ElevenLabs v4: Finishes first. Gemini 3.1 Flash: No stop message.
Gemini 3.1 Flash. ElevenLabs v4: 80.4%. Gemini 3.1 Flash: 87.7%.
ElevenLabs v4. ElevenLabs v4: $80.00. Gemini 3.1 Flash: $86.16.