I found a small UI mistake in Vapi: when using elevenlabs voices, it is possible to set "optimize streaming latency" between 1 and 4. 1 means less optimization (and more latency) and 4 means max optimization. However, in the Vapi UI, lower values are associated with "less latency". https://elevenlabs.io/docs/api-reference/streaming https://cdn.discordapp.com/attachments/1211484481848873020/1240960241508548679/image.png?ex=664875c9&is=66472449&hm=35c425ba60a10d307e568731ffac030f805200826d560554b72449648a5002f3&