Fact · Voice and AI
The Moshi paper says that the complexity of current spoken dialogue pipelines induces a latency of several seconds between interactions.
Checked against its source on October 17, 2026
In the source's own words
“First, their complexity induces a latency of several seconds between interactions.”
Moshi: a speech-text foundation model for real-time dialogue, Alexandre Défossez and and colleagues at Kyutai, arXiv (Kyutai), 2024, Abstract, first problem listed.
Open the original- What it measures
- Kyutai's 2024 paper argues that a chain of separate components for voice activity detection, speech recognition, dialogue and speech synthesis is slow for conversation.
- What it does not show
- This is the authors' description of the pipeline design they argue against. The paper does not give a single measured figure for a particular commercial product.