diff --git a/.changeset/lemonslice-audio-output-order.md b/.changeset/lemonslice-audio-output-order.md
new file mode 100644
index 000000000..73b0cc211
--- /dev/null
+++ b/.changeset/lemonslice-audio-output-order.md
@@ -0,0 +1,5 @@
+---
+'@livekit/agents-plugin-lemonslice': patch
+---
+
+fix(lemonslice): bind avatar audio output before starting upstream session
diff --git a/plugins/lemonslice/src/avatar.ts b/plugins/lemonslice/src/avatar.ts
index e4d6a970b..d86f5d9b2 100644
--- a/plugins/lemonslice/src/avatar.ts
+++ b/plugins/lemonslice/src/avatar.ts
@@ -186,8 +186,8 @@ export class AvatarSession extends voice.AvatarSession {
    *
    * This method:
    * 1. Creates a LiveKit token for the avatar participant
-   * 2. Calls the LemonSlice API to start the avatar session
-   * 3. Configures the agent's audio output to stream to the avatar
+   * 2. Configures the agent's audio output to stream to the avatar
+   * 3. Calls the LemonSlice API to start the avatar session
    *
    * @param agentSession - The agent session to connect to the avatar
    * @param room - The LiveKit room where the avatar will join
@@ -249,9 +249,8 @@ export class AvatarSession extends voice.AvatarSession {
 
     const livekitToken = await at.toJwt();
 
-    this.#logger.debug('starting avatar session');
-    const sessionId = await this.startAgent(livekitUrl, livekitToken);
-
+    // Bind audio output before the upstream HTTP call so subsequent generations route to
+    // the avatar identity while DataStreamAudioOutput waits for the video track.
     agentSession.output.audio = new voice.DataStreamAudioOutput({
       room,
       destinationIdentity: this.avatarIdentity,
@@ -260,6 +259,9 @@ export class AvatarSession extends voice.AvatarSession {
       waitPlaybackStart: true,
     });
 
+    this.#logger.debug('starting avatar session');
+    const sessionId = await this.startAgent(livekitUrl, livekitToken);
+
     return sessionId;
   }