Skip to content
Hot storyPast story

Inworld publishes TTS-2 Flash results on the Cekura benchmark

1 report1 sourceUpdated 16 d ago

What happened

AI overview

Inworld has published results for its in-house realtime voice model Realtime TTS-2 Flash on a newly launched independent voice benchmark from Cekura: 46ms time to first audio and 93.2% accuracy on difficult text. The results were released by Inworld itself and have not been independently reviewed. Cekura says the benchmark covers more than 50 models from vendors including OpenAI, Google, Nvidia, xAI and Inworld, and allows comparison of naturalness, performance and cost across speech-to-speech, speech-to-text and text-to-speech models as well as voice agent platforms. Inworld also congratulated Cekura on the launch and said better evaluation helps everyone build better voice agents.

AI-written from the coverage · updated 16 d ago

Coverage timeline

Follow the coverage to see the story from different sides.

Nov 6
  1. Inworld AIPick
    Inworld says Realtime TTS-2 Flash starts speaking in 46ms with 93.2% accuracy on hard text on Cekura voice benchmark

    Inworld published Realtime TTS-2 Flash's results on Cekura's new independent voice benchmark: 46ms to start speaking and 93.2% accuracy on hard text. Cekura says the benchmark covers 50+ models from vendors including OpenAI, Google, Nvidia, xAI and Inworld, and allows comparison of naturalness, performance and cost across speech-to-speech, speech-to-text and text-to-speech models and voice agent platforms. Inworld also congratulated the Cekura team on launching the benchmark, saying better evaluation helps everyone build better voice agents.