diff --git a/README.md b/README.md
index be1740d..e101cec 100644
--- a/README.md
+++ b/README.md
@@ -59,8 +59,8 @@ Recommended comparison order:
 3. `voxtral-small` (`mistralai/Voxtral-Small-24B-2507`)
 
 Qwen2-Audio and Voxtral are called through an OpenAI-compatible
-`/v1/chat/completions` endpoint with `input_audio`; set their endpoint URLs only
-after the models are actually exposed on the AI server.
+`/v1/chat/completions` endpoint with vLLM-style `audio_url` data URLs; set
+their endpoint URLs only after the models are actually exposed on the AI server.
 
 AI-server compose snippets for these temporary comparison endpoints live in
 `deploy/ai-server/docker-compose.audio.yml`. They are profile-gated because the