Left is faster. Higher reads more hard parts right.
ElevenLabs v4 Turbo is better on streaming latency. AssemblyAI TTS 1 is better on non-streaming latency, stopping, accuracy, naturalness 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.
AssemblyAI TTS 1. ElevenLabs v4 Turbo: 176 ms. AssemblyAI TTS 1: 171 ms.
AssemblyAI TTS 1. ElevenLabs v4 Turbo: 176 ms. AssemblyAI TTS 1: 171 ms.
ElevenLabs v4 Turbo. ElevenLabs v4 Turbo: 69 ms. AssemblyAI TTS 1: 159 ms.
AssemblyAI TTS 1. ElevenLabs v4 Turbo: Finishes first. AssemblyAI TTS 1: 40 ms.
AssemblyAI TTS 1. ElevenLabs v4 Turbo: 79.9%. AssemblyAI TTS 1: 81.5%.
AssemblyAI TTS 1. ElevenLabs v4 Turbo: $40.00. AssemblyAI TTS 1: $15.00.
Cekura runs these simulated calls on your agent and scores every one.