Nous Research adds streaming speech to speed Hermes Agent voice chats
The open-source agent starts speaking while it generates an answer, reducing the dead air that makes AI voice interfaces feel slow.
By Ryan Merket · Published
Primary source: X
Why it matters
Voice latency is a product problem as much as a model problem. Streaming lets Nous make Hermes feel faster while it builds paid hosting around an open-source, provider-agnostic agent.
Ryan "Teknium" Teknium (@Teknium), a Nous Research co-founder and its head of post-training, said on X Wednesday that Hermes Agent voice chats now stream speech from most API-based text-to-speech backends, bringing the open-source assistant closer to a live conversation.…
When you purchase through links in our articles, we may earn a small commission. This doesn’t affect our editorial independence.