Left is faster. Higher reads more hard parts right.
ElevenLabs v4 Turbo is better on streaming latency. Inworld TTS-2 is better on non-streaming latency, 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.
Inworld TTS-2. ElevenLabs v4 Turbo: 176 ms. Inworld TTS-2: 126 ms.
Inworld TTS-2. ElevenLabs v4 Turbo: 176 ms. Inworld TTS-2: 126 ms.
ElevenLabs v4 Turbo. ElevenLabs v4 Turbo: 69 ms. Inworld TTS-2: 127 ms.
Neither has a figure. ElevenLabs v4 Turbo: Finishes first. Inworld TTS-2: No stop message.
Inworld TTS-2. ElevenLabs v4 Turbo: 79.9%. Inworld TTS-2: 93.4%.
Inworld TTS-2. ElevenLabs v4 Turbo: $40.00. Inworld TTS-2: $25.00.